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

    Neuronpedia

    INDEX
    Explanations

    references to the Fox network or its related properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocal
    -0.17
    ninger
    -0.17
    bove
    -0.16
    antu
    -0.16
     thủy
    -0.15
    ont
    -0.15
    еÑĢж
    -0.15
    ered
    -0.14
    vens
    -0.14
    leine
    -0.14
    POSITIVE LOGITS
    conn
    0.22
    es
    0.19
    xy
    0.19
    croft
    0.18
    worthy
    0.18
    enberg
    0.17
    CONN
    0.17
     Trot
    0.16
    boro
    0.16
    usher
    0.16
    Act Density 0.009%

    No Known Activations