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

    Neuronpedia

    INDEX
    Explanations

    emoticons or punctuation marks that convey emotions or tone

    oai_token-act-pair · gpt-3.5-turbo

    special characters and non-English letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     makeup
    -0.73
     Prometheus
    -0.69
     velvet
    -0.69
    holm
    -0.67
    creen
    -0.65
     Krug
    -0.64
     BMC
    -0.64
     Copenhagen
    -0.64
     shroud
    -0.64
     Berm
    -0.63
    POSITIVE LOGITS
    Ĥ
    1.83
    Ħ
    1.70
    Ģ
    1.65
    ģ
    1.64
    Ĥİ
    1.62
    ĥ
    1.60
    £
    1.58
    ¾
    1.54
    ¼
    1.52
    ²
    1.50
    Act Density 0.012%

    No Known Activations