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

    Neuronpedia

    INDEX
    Explanations

    numerical values or terms related to hitting high records

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to reaching or hitting specific metrics or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onga
    -0.81
    atu
    -0.71
    croft
    -0.70
     endeav
    -0.67
     artic
    -0.65
    urat
    -0.64
    cell
    -0.64
    uristic
    -0.63
    fo
    -0.63
    rying
    -0.62
    POSITIVE LOGITS
    peak
    0.77
     midnight
    0.76
     peaks
    0.72
     Babel
    0.72
    ebin
    0.72
     puberty
    0.71
     coincide
    0.71
     climax
    0.70
     landfall
    0.69
     exhaustion
    0.68
    Act Density 0.069%

    No Known Activations