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

    Neuronpedia

    INDEX
    Explanations

    references to objective concepts and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edback
    -0.15
    еÑĪ
    -0.15
    song
    -0.14
    sun
    -0.14
     éĢ
    -0.14
    aldi
    -0.14
    uen
    -0.14
    .NoArgsConstructor
    -0.13
     ÑĨÑĸ
    -0.13
     Rosenberg
    -0.13
    POSITIVE LOGITS
    OURSE
    0.15
     Pom
    0.15
     Pierce
    0.14
    cura
    0.14
    Bindable
    0.14
     Finger
    0.14
    astos
    0.14
    VERR
    0.14
    rios
    0.14
    ivan
    0.14
    Act Density 0.012%

    No Known Activations