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

    Neuronpedia

    INDEX
    Explanations

    email-related actions like "adding" or "registering."

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating an action of contribution or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pru
    -0.64
     fixme
    -0.64
     Shooter
    -0.64
     Fixes
    -0.62
     Thief
    -0.61
     Consent
    -0.60
     Dise
    -0.60
     Shogun
    -0.60
     Rider
    -0.58
     gon
    -0.58
    POSITIVE LOGITS
    ipl
    0.76
    ipple
    0.76
    OTOS
    0.69
    ilde
    0.69
    iland
    0.68
    APH
    0.66
    aft
    0.66
    hest
    0.65
    onz
    0.64
    ites
    0.64
    Act Density 0.000%

    No Known Activations