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

    Neuronpedia

    INDEX
    Explanations

    references to boycotts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to boycotts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uscript
    -0.78
    ocre
    -0.75
    ixture
    -0.72
    ancial
    -0.68
    ixed
    -0.68
    ptroller
    -0.67
     guid
    -0.65
     confir
    -0.64
    ahime
    -0.64
    opter
    -0.63
    POSITIVE LOGITS
     boycott
    0.99
    wana
    0.94
    cott
    0.94
     boycot
    0.89
    aliation
    0.75
    ting
    0.75
    halla
    0.74
    kel
    0.69
    ters
    0.68
     repr
    0.68
    Act Density 0.015%

    No Known Activations