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

    Neuronpedia

    INDEX
    Explanations

    concepts related to future research directions and pending work

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    binant
    -0.62
     ProtoMessage
    -0.61
    Datuak
    -0.59
     himſelf
    -0.59
     Efq
    -0.59
    lgari
    -0.57
     myſelf
    -0.57
     Administrativna
    -0.57
     soon
    -0.56
     sooner
    -0.55
    POSITIVE LOGITS
    fromnode
    0.66
     interesar
    0.61
     betweenstory
    0.57
    posedge
    0.52
     marcó
    0.52
    geot
    0.50
    احبه
    0.50
     sugg
    0.48
     dica
    0.47
     vecka
    0.47
    Act Density 0.023%

    No Known Activations