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

    Neuronpedia

    INDEX
    Explanations

    words related to rejection or being denied

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipel
    -0.76
    llular
    -0.70
    isf
    -0.70
    isd
    -0.69
    ortal
    -0.67
    brance
    -0.67
    ussen
    -0.66
    inki
    -0.66
    ikk
    -0.66
    ibrary
    -0.65
    POSITIVE LOGITS
     outright
    0.79
    kus
    0.72
    Ĥª
    0.68
     rejection
    0.67
     validation
    0.67
     unanimously
    0.66
    âķIJâķIJ
    0.66
    lect
    0.65
     excuses
    0.64
    ively
    0.62
    Act Density 0.025%

    No Known Activations