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

    Neuronpedia

    INDEX
    Explanations

    references to document structures and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.58
    -
    -0.55
     
    -0.53
     B
    -0.53
    .
    -0.52
    ,
    -0.51
    /
    -0.50
     and
    -0.49
    ’
    -0.48
    _
    -0.48
    POSITIVE LOGITS
     ModelExpression
    1.45
    ConstraintMaker
    1.42
     MainAxisSize
    1.36
     myſelf
    1.34
    ſelf
    1.26
    extAlignment
    1.23
    Personendaten
    1.23
    awtextra
    1.21
     ―――――
    1.20
     Efq
    1.19
    Act Density 0.016%

    No Known Activations