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

    Neuronpedia

    INDEX
    Explanations

    comparisons or contrasts in the form of "more than" statements

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that highlight the complexity or severity of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMENT
    -0.81
    antage
    -0.79
    imity
    -0.76
    uto
    -0.76
    ance
    -0.71
    FTWARE
    -0.70
    urther
    -0.70
    ulpt
    -0.69
    bilt
    -0.69
    autions
    -0.68
    POSITIVE LOGITS
     usual
    0.91
     anything
    0.75
     ours
    0.73
     ordinary
    0.72
     placebo
    0.72
     superficial
    0.71
    average
    0.71
     ever
    0.70
    ĻĤ
    0.70
     Watergate
    0.67
    Act Density 0.067%

    No Known Activations