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

    Neuronpedia

    INDEX
    Explanations

    information or instructions presented sequentially like a step-by-step guide

    oai_token-act-pair · gpt-3.5-turbo

    instructions or guides related to various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.76
    stood
    -0.60
     thri
    -0.58
    ).[
    -0.56
    ourke
    -0.55
    remlin
    -0.55
     nods
    -0.55
    ''.
    -0.54
     UNCLASSIFIED
    -0.53
     undermines
    -0.53
    POSITIVE LOGITS
     Patreon
    0.75
    FAQ
    0.70
     Discord
    0.65
    ython
    0.65
     ðŁĻĤ
    0.64
     myself
    0.62
    hess
    0.62
     :)
    0.61
     github
    0.60
     HUGE
    0.59
    Act Density 1.307%

    No Known Activations