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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing certainty or clarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or clarity about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mouth
    -0.80
    aukee
    -0.78
    andem
    -0.76
    cience
    -0.68
    rack
    -0.65
    izont
    -0.63
    uminati
    -0.61
    UV
    -0.60
    utorial
    -0.60
    aciously
    -0.60
    POSITIVE LOGITS
     whoever
    0.92
     there
    0.76
     none
    0.69
     omission
    0.69
     these
    0.69
     nobody
    0.68
     although
    0.67
     someone
    0.66
     we
    0.65
     they
    0.65
    Act Density 0.189%

    No Known Activations