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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical projection and mappings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Mor
    -0.65
     Des
    -0.57
    chlag
    -0.56
     Amor
    -0.52
     Werk
    -0.51
     Cha
    -0.50
    ilog
    -0.50
     char
    -0.47
     Man
    -0.47
    oflu
    -0.47
    POSITIVE LOGITS
    StructEnd
    0.94
    TagMode
    0.82
     propOrder
    0.81
     Efq
    0.78
     Theſe
    0.77
    BeginContext
    0.76
    Geplaatst
    0.73
     myſelf
    0.71
     ſmall
    0.71
     tramontina
    0.69
    Act Density 0.012%

    No Known Activations