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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vellous
    -0.73
    */].
    -0.71
     Honourable
    -0.70
     Honours
    -0.69
     InputDecoration
    -0.69
    DNEY
    -0.68
    centred
    -0.67
    Aluminium
    -0.67
    favourite
    -0.67
     tonnes
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.63
    ConstraintMaker
    0.55
    <eos>
    0.48
    ?
    0.47
    JspWriter
    0.46
    .
    0.45
    SpringBoot
    0.44
     if
    0.42
     clerical
    0.41
     atmos
    0.41
    Act Density 0.401%

    No Known Activations