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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.75
     Crossing
    -0.69
     Coliseum
    -0.61
     Hitch
    -0.60
     Ethiopian
    -0.59
     Obst
    -0.58
     Auditor
    -0.58
     ult
    -0.58
     Riy
    -0.58
     Crunch
    -0.58
    POSITIVE LOGITS
    abouts
    0.94
    well
    0.74
     livest
    0.69
    not
    0.65
    ene
    0.65
    est
    0.64
    Not
    0.61
    BE
    0.60
    't
    0.60
    enth
    0.59
    Act Density 0.072%

    No Known Activations