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

    Neuronpedia

    INDEX
    Explanations

    phrases related to caution or warning

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases expressing warnings and feelings of despair

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ermanent
    -0.73
    ãĥĥãĤ¯
    -0.68
     Roads
    -0.66
     corrid
    -0.62
    ilar
    -0.62
    ORPG
    -0.62
     jerk
    -0.62
     grievance
    -0.61
     deductions
    -0.61
    porary
    -0.60
    POSITIVE LOGITS
    lust
    1.08
    lessly
    0.86
    iful
    0.80
     lest
    0.76
     beware
    0.74
    LESS
    0.74
     Despair
    0.73
    ful
    0.72
    lihood
    0.72
     Chrys
    0.72
    Act Density 0.054%

    No Known Activations