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

    Neuronpedia

    INDEX
    Explanations

    words related to rejection or refusal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rejection and disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isd
    -0.71
    isf
    -0.71
    vern
    -0.71
    ipel
    -0.71
    ortal
    -0.71
    ussen
    -0.70
     encyclopedia
    -0.70
    vity
    -0.68
    amen
    -0.67
    brance
    -0.67
    POSITIVE LOGITS
     outright
    0.82
     rejection
    0.77
     validation
    0.69
    kus
    0.68
     acceptance
    0.67
    âķIJâķIJ
    0.67
     excuses
    0.67
     temptation
    0.66
    Ĥª
    0.66
     straw
    0.65
    Act Density 0.032%

    No Known Activations