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

    Neuronpedia

    INDEX
    Explanations

    question marks and interrogative expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.07
    3:0.08
    4:0.07
    5:0.05
    6:0.02
    7:0.32
    8:0.06
    9:0.06
    10:0.07
    11:0.11
    Negative Logits
    growth
    -1.55
    piration
    -1.51
     inception
    -1.46
    aign
    -1.30
    commerce
    -1.30
    ivated
    -1.29
    aughed
    -1.25
    429
    -1.25
    apsed
    -1.25
    borgh
    -1.24
    POSITIVE LOGITS
     Beware
    1.55
     confidentiality
    1.47
    DragonMagazine
    1.44
     caveats
    1.44
     perpend
    1.40
     Lords
    1.37
     beware
    1.35
    ��
    1.35
     Polic
    1.34
    五
    1.33
    Act Density 0.004%

    No Known Activations