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

    Neuronpedia

    INDEX
    Explanations

    phrases related to provocative actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with provocation and suggestive behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redits
    -0.77
    yer
    -0.75
    ©¶æ
    -0.74
    ership
    -0.73
    oard
    -0.73
    VERTISEMENT
    -0.72
    abol
    -0.71
    orah
    -0.71
    ords
    -0.69
    elsen
    -0.68
    POSITIVE LOGITS
     provocative
    1.25
     provocation
    1.13
     suggestive
    0.78
     satir
    0.77
     warnings
    0.76
     readings
    0.76
     undermin
    0.75
     arous
    0.75
     mischief
    0.74
     sidx
    0.74
    Act Density 0.010%

    No Known Activations