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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.89
    INT
    -0.81
    clerosis
    -0.81
    endar
    -0.80
    Reviewer
    -0.80
    ILA
    -0.77
    zac
    -0.75
    amina
    -0.74
    apsed
    -0.73
    ructose
    -0.73
    POSITIVE LOGITS
    ly
    0.97
     fallout
    0.78
    ingly
    0.77
    erness
    0.77
    lly
    0.76
    ially
    0.75
     doom
    0.75
     shorth
    0.74
    ively
    0.74
     hypot
    0.72
    Act Density 0.014%

    No Known Activations