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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activism

    oai_token-act-pair · gpt-3.5-turbo

    words related to activism and activists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grind
    -0.79
    MER
    -0.73
     Manor
    -0.72
     Terr
    -0.69
     Ness
    -0.69
     Bake
    -0.67
    lihood
    -0.65
     Fair
    -0.64
     Tiger
    -0.63
     Bigfoot
    -0.63
    POSITIVE LOGITS
     Activ
    1.26
     activ
    1.02
    activation
    0.95
    ists
    0.95
    Activ
    0.91
    activ
    0.89
    ileaks
    0.87
    ist
    0.85
    edIn
    0.82
     activation
    0.81
    Act Density 0.011%

    No Known Activations