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

    Neuronpedia

    INDEX
    Explanations

    contractions of 'don't' in sentences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or reluctance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agency
    -0.71
     afore
    -0.67
     Passage
    -0.66
    ategory
    -0.66
     misdem
    -0.65
     ANG
    -0.63
    )=(
    -0.60
     Anim
    -0.59
     Passing
    -0.59
     Traps
    -0.58
    POSITIVE LOGITS
    't
    1.35
    ned
    0.93
    uts
    0.85
    ÃŃ
    0.84
    ates
    0.83
    nas
    0.81
    anted
    0.78
    nat
    0.75
    etsk
    0.74
    osphere
    0.74
    Act Density 0.082%

    No Known Activations