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

    Neuronpedia

    INDEX
    Explanations

    descriptive words associated with emotional states and physical postures or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irst
    -0.18
    annis
    -0.16
    ILTER
    -0.16
    ines
    -0.15
    leness
    -0.15
    ookies
    -0.15
    crast
    -0.15
    pole
    -0.15
    dv
    -0.15
    ulia
    -0.14
    POSITIVE LOGITS
     Giov
    0.15
    ÑĩеÑĤ
    0.14
    νον
    0.14
    .Annotations
    0.14
    egie
    0.14
    alsy
    0.13
    ÑĢеж
    0.13
    oir
    0.13
    horse
    0.13
     YYS
    0.13
    Act Density 0.170%

    No Known Activations