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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only" and its context within a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vectorielles
    -0.89
     couverte
    -0.74
     vaikka
    -0.72
     <<<<<<<<<<<<<<
    -0.68
     vekt
    -0.68
    ruptedException
    -0.67
     vectorielle
    -0.66
     Philist
    -0.64
     écl
    -0.64
     abstrait
    -0.63
    POSITIVE LOGITS
    SourceChecksum
    0.80
    satunya
    0.79
     sole
    0.77
    唯一的
    0.76
    唯一
    0.75
     enige
    0.66
     remaining
    0.66
     einzigen
    0.66
     eneste
    0.66
     jedin
    0.65
    Act Density 0.119%

    No Known Activations