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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing relief or disappointment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of exasperation or resignation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    friends
    -0.80
    wives
    -0.79
    cycl
    -0.79
    lif
    -0.77
    facts
    -0.73
    jas
    -0.71
    LET
    -0.68
    eve
    -0.66
    chn
    -0.65
    fixed
    -0.65
    POSITIVE LOGITS
     aloud
    0.87
     shrug
    0.84
    kowski
    0.79
     sigh
    0.73
     bask
    0.73
     bitterly
    0.73
     nervously
    0.70
     sarcast
    0.69
    acket
    0.68
     scorn
    0.68
    Act Density 0.021%

    No Known Activations