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

    Neuronpedia

    INDEX
    Explanations

    actions or motions related to going somewhere or doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.59
    儡
    -0.57
     täh
    -0.52
     fehler
    -0.51
    arrivo
    -0.51
     ogrodow
    -0.51
     Dort
    -0.49
     mergeFrom
    -0.48
     Canaan
    -0.48
    Ligações
    -0.48
    POSITIVE LOGITS
    Went
    0.78
     go
    0.78
    Goes
    0.78
     Went
    0.74
    went
    0.72
     WENT
    0.72
    encodeWith
    0.70
     went
    0.69
     lengths
    0.67
     GenerationType
    0.67
    Act Density 0.133%

    No Known Activations