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

    Neuronpedia

    INDEX
    Explanations

    summaries or condensed descriptions of information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     &
    -0.48
    =\"
    -0.46
     Nap
    -0.44
     ke
    -0.43
    aconda
    -0.43
     bra
    -0.42
    onica
    -0.42
    Revue
    -0.42
     zaj
    -0.42
    Tres
    -0.42
    POSITIVE LOGITS
     Савезне
    1.09
     <<<<<<<<<<<<<<
    0.99
    NameInMap
    0.99
     Monfieur
    0.99
     ſche
    0.98
    EDEFAULT
    0.97
     ſeveral
    0.97
     itſelf
    0.96
     pleaſure
    0.93
     myſelf
    0.92
    Act Density 0.048%

    No Known Activations