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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulace
    -0.17
    osit
    -0.16
    essen
    -0.14
    lene
    -0.14
    ula
    -0.14
     Richards
    -0.14
    ÑıÑī
    -0.13
    ependency
    -0.13
     íļ
    -0.13
    ode
    -0.13
    POSITIVE LOGITS
    thouse
    0.20
    safe
    0.15
     ÑģебÑı
    0.15
    APS
    0.15
     toc
    0.15
    оÑĤÑĥ
    0.14
     rằng
    0.14
    çµ
    0.14
    rait
    0.14
    quot
    0.14
    Act Density 0.037%

    No Known Activations