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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confessions or discipline

    oai_token-act-pair · gpt-3.5-turbo

    statements of confession or admission of guilt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unison
    -0.73
    agonists
    -0.65
    %%
    -0.64
    oops
    -0.63
    UGC
    -0.63
    è£ħ
    -0.62
    skirts
    -0.62
     Whedon
    -0.61
    choes
    -0.60
    etheless
    -0.60
    POSITIVE LOGITS
     himself
    1.39
     his
    1.14
     Himself
    0.99
    His
    0.92
     ..."
    0.91
    his
    0.90
     [
    0.88
    .''
    0.84
     us
    0.80
     His
    0.80
    Act Density 0.523%

    No Known Activations