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

    Neuronpedia

    INDEX
    Explanations

    phrases related to impact and positive change within communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mann
    -0.18
    fol
    -0.17
    浦
    -0.17
    éric
    -0.16
    ataka
    -0.16
    avored
    -0.15
    frau
    -0.15
    utura
    -0.15
    ñana
    -0.15
     FAG
    -0.14
    POSITIVE LOGITS
     Xem
    0.15
    erti
    0.15
    enti
    0.15
    aÄį
    0.14
    اضÛĮ
    0.14
    umba
    0.14
     Charg
    0.14
    ông
    0.13
    equip
    0.13
     campaign
    0.13
    Act Density 0.480%

    No Known Activations