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

    Neuronpedia

    INDEX
    Explanations

    method definitions and structure in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.76
    -
    -0.67
     
    -0.67
    l
    -0.64
    ,
    -0.55
     “
    -0.54
    ↵
    -0.54
     –
    -0.53
    _
    -0.52
     and
    -0.52
    POSITIVE LOGITS
    OGND
    1.26
    +#+
    1.26
    ArgsConstructor
    1.24
    ConstraintMaker
    1.22
    tagHelperRunner
    1.21
    MessageTagHelper
    1.19
     myſelf
    1.16
     autorytatywna
    1.15
     itſelf
    1.14
     мәкал
    1.13
    Act Density 0.385%

    No Known Activations