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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases expressing personal opinions or feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal reflection and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiIcon
    -0.77
     BaseType
    -0.70
     Emin
    -0.70
    ewitness
    -0.66
    Protect
    -0.65
    assadors
    -0.65
    ormal
    -0.62
    ultan
    -0.62
    aceae
    -0.61
     Supports
    -0.61
    POSITIVE LOGITS
     disappointed
    1.27
     nervous
    1.27
     annoyed
    1.22
     apprehens
    1.15
     bum
    1.14
     bored
    1.12
     hesitant
    1.11
     surprised
    1.09
     frustrated
    1.08
     conflicted
    1.08
    Act Density 0.292%

    No Known Activations