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

    Neuronpedia

    INDEX
    Explanations

    evidence of effectiveness or success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.68
     McCarthy
    -0.58
    /
    -0.57
     
    -0.56
     Katz
    -0.55
    (
    -0.54
    Katz
    -0.53
     [
    -0.52
     co
    -0.51
     f
    -0.50
    POSITIVE LOGITS
     proved
    1.79
     proves
    1.74
     Prove
    1.63
     prove
    1.58
     proving
    1.56
     proven
    1.52
     Proving
    1.52
    prove
    1.46
    Prove
    1.43
    proved
    1.42
    Act Density 0.137%

    No Known Activations