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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or strong possibility

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating certainty or conclusions about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.78
    arak
    -0.74
    à¦
    -0.68
    mouth
    -0.67
    usk
    -0.67
    andem
    -0.67
    rack
    -0.67
    Zone
    -0.66
    oses
    -0.66
    cience
    -0.65
    POSITIVE LOGITS
     whoever
    1.02
     there
    0.81
     these
    0.78
     somebody
    0.75
     someone
    0.75
     they
    0.74
     nobody
    0.73
     although
    0.69
     we
    0.69
     none
    0.69
    Act Density 0.211%

    No Known Activations