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

    Neuronpedia

    INDEX
    Explanations

    negatively framed statements regarding social behaviors and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĬÙĦÙħ
    -0.15
    ifar
    -0.15
    ']!='
    -0.14
    rey
    -0.14
    Raw
    -0.14
    ARRIER
    -0.14
    .targets
    -0.14
     Rooney
    -0.13
    ze
    -0.13
    cete
    -0.13
    POSITIVE LOGITS
     McMahon
    0.18
     anymore
    0.15
     District
    0.15
    District
    0.15
     Bez
    0.14
    orde
    0.14
     any
    0.14
    798
    0.13
    lazy
    0.13
     Dancing
    0.13
    Act Density 0.388%

    No Known Activations