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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activism or activist movements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oaks
    -0.71
     Ness
    -0.68
     Grind
    -0.67
     Hercules
    -0.66
     Carol
    -0.65
     Bake
    -0.65
     Neighbor
    -0.65
     Stafford
    -0.65
    lihood
    -0.65
     Tiger
    -0.64
    POSITIVE LOGITS
    ists
    1.12
    ision
    1.09
    ist
    1.05
    ivation
    1.00
    uates
    0.99
    ivated
    0.95
    tion
    0.95
    activ
    0.95
    ité
    0.94
    ated
    0.93
    Act Density 0.012%

    No Known Activations