Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the phrase "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    different variations of referring to or naming someone

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.04
    3:0.05
    4:0.39
    5:0.08
    6:0.03
    7:0.02
    8:0.12
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
    okane
    -1.46
    ortun
    -1.37
    checks
    -1.37
    Catalog
    -1.33
    check
    -1.33
     foundations
    -1.31
    abus
    -1.31
    gm
    -1.31
    jri
    -1.30
    iscovery
    -1.30
    POSITIVE LOGITS
    ت
    1.43
     Disorder
    1.42
     Intelligence
    1.40
    Lat
    1.38
     Painting
    1.38
     Piercing
    1.37
     Threat
    1.37
     Bow
    1.36
    ruciating
    1.28
     RTX
    1.27
    Act Density 0.005%

    No Known Activations