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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repeated events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate repetition or frequency of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XT
    -0.85
    Reviewer
    -0.83
    agra
    -0.77
    Marginal
    -0.71
    aceous
    -0.69
    ourt
    -0.69
     heirs
    -0.68
    ITAL
    -0.67
    andr
    -0.65
    ains
    -0.65
    POSITIVE LOGITS
     consecut
    1.02
    points
    0.87
     throughout
    0.80
    cale
    0.80
    coded
    0.78
     apiece
    0.74
    orial
    0.71
     before
    0.69
    pan
    0.69
    manship
    0.68
    Act Density 0.045%

    No Known Activations