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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating value or worthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.78
     gynhyrchwyd
    -0.71
    thentication
    -0.68
     Bielefeld
    -0.67
     Shakspeare
    -0.67
     Landau
    -0.67
     Delia
    -0.67
     AGC
    -0.66
     shewn
    -0.65
    felde
    -0.65
    POSITIVE LOGITS
     worth
    1.69
     Worth
    1.56
     WORTH
    1.53
    Worth
    1.43
    worth
    1.34
    WORTH
    1.32
     worthwhile
    0.99
     Worthy
    0.93
     wort
    0.88
     vaut
    0.83
    Act Density 0.044%

    No Known Activations