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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions that happen suddenly and energetically

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a dramatic entrance or emergence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.67
     Factors
    -0.65
    manship
    -0.64
    ryu
    -0.62
    trip
    -0.60
    £
    -0.59
    thood
    -0.58
    trust
    -0.58
    ials
    -0.57
    essors
    -0.56
    POSITIVE LOGITS
    wards
    0.72
     flames
    0.71
    Downloadha
    0.68
     hither
    0.68
     ecstasy
    0.67
    ibrary
    0.67
     shores
    0.67
     Archdemon
    0.65
     applause
    0.65
    nova
    0.65
    Act Density 0.282%

    No Known Activations