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

    Neuronpedia

    INDEX
    Explanations

    references to qualifications or conditions related to eligibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encouragement
    -0.75
     Forgiveness
    -0.69
    interpretation
    -0.69
    adaptation
    -0.69
     interception
    -0.68
     stabilisation
    -0.68
    inversion
    -0.68
    engagement
    -0.66
     Suppression
    -0.66
    acceleration
    -0.65
    POSITIVE LOGITS
     оригіналу
    0.40
    DAY
    0.39
    InSection
    0.38
    DAYS
    0.37
    Days
    0.36
    ungsbedingungen
    0.36
    GOING
    0.34
    œuvre
    0.33
    xFE
    0.33
    InjectAttribute
    0.32
    Act Density 0.810%

    No Known Activations