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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating methods or styles of doing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unica
    -0.71
     nahilalakip
    -0.65
    까지
    -0.60
    riwal
    -0.59
    "]}
    -0.53
    brida
    -0.53
    にかけて
    -0.53
    SUCCESS
    -0.50
    roslav
    -0.50
    dsc
    -0.49
    POSITIVE LOGITS
     Quite
    0.73
     WAY
    0.72
     quite
    0.71
    Way
    0.70
    Quite
    0.70
    quite
    0.69
     ridiculously
    0.68
     awfully
    0.67
     numberWith
    0.66
     långt
    0.66
    Act Density 0.166%

    No Known Activations