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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or suggestion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "say" followed by a numerical value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.81
    lete
    -0.79
    Write
    -0.77
    Äĩ
    -0.74
    quet
    -0.74
    omsky
    -0.70
    RM
    -0.68
    Bind
    -0.67
    vez
    -0.66
    irs
    -0.66
    POSITIVE LOGITS
     dozen
    0.68
     Leilan
    0.67
     Aph
    0.64
     uh
    0.59
     fractions
    0.58
     controlling
    0.57
     Rug
    0.55
    ties
    0.55
     Deg
    0.55
     tapping
    0.55
    Act Density 0.066%

    No Known Activations