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

    Neuronpedia

    INDEX
    Explanations

    references to older individuals and their interactions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.08
    3:0.04
    4:0.05
    5:0.04
    6:0.38
    7:0.05
    8:0.05
    9:0.03
    10:0.09
    11:0.07
    Negative Logits
    ongyang
    -1.47
    ccoli
    -1.38
    ixt
    -1.35
    uese
    -1.30
    ospons
    -1.30
    ocument
    -1.25
    ILA
    -1.25
    bably
    -1.23
    itionally
    -1.19
    ット
    -1.18
    POSITIVE LOGITS
    than
    1.72
     wiser
    1.33
    ner
    1.31
    types
    1.24
    rant
    1.21
    deb
    1.20
     Baptist
    1.17
    rants
    1.17
    cases
    1.16
     necks
    1.14
    Act Density 0.014%

    No Known Activations