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

    Neuronpedia

    INDEX
    Explanations

    words related to interviews and statements from various news sources

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns or possessive constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sson
    -0.79
    anges
    -0.79
    mo
    -0.77
    linked
    -0.69
    ro
    -0.69
    ovi
    -0.68
    dylib
    -0.67
    forest
    -0.66
    ppo
    -0.66
    ol
    -0.66
    POSITIVE LOGITS
     newest
    1.02
     own
    0.94
     finest
    0.90
     flagship
    0.90
     latest
    0.88
     biggest
    0.86
     sake
    0.83
     signature
    0.80
    ogyn
    0.80
     official
    0.79
    Act Density 0.157%

    No Known Activations