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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various positions of advantage or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _SAFE
    -0.07
    nemonic
    -0.07
     ваг
    -0.06
     éĻIJ
    -0.06
    Ñĥва
    -0.06
    fdb
    -0.06
     connexion
    -0.06
    fet
    -0.06
    eties
    -0.06
    reau
    -0.06
    POSITIVE LOGITS
     position
    0.16
     positions
    0.13
     Position
    0.12
    position
    0.12
     posición
    0.10
     ability
    0.10
     POSITION
    0.10
    Position
    0.10
     posição
    0.10
    .position
    0.10
    Act Density 0.010%

    No Known Activations