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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities and concepts in a discussion

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.92
     Efq
    -0.82
     itſelf
    -0.82
     Chriſt
    -0.77
     Signalez
    -0.77
     Monfieur
    -0.75
    adpleegd
    -0.75
     Houſe
    -0.75
    andowski
    -0.74
     houſe
    -0.74
    POSITIVE LOGITS
     this
    0.55
     and
    0.52
    /
    0.48
     
    0.46
    ,
    0.45
    h
    0.45
    <eos>
    0.44
    or
    0.44
    Paginator
    0.44
     to
    0.42
    Act Density 0.168%

    No Known Activations