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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional conflict or introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awah
    -0.19
    erras
    -0.17
     Grim
    -0.14
    ikh
    -0.14
    ystick
    -0.14
    YY
    -0.14
    alion
    -0.13
    alim
    -0.13
     εξ
    -0.13
    ura
    -0.13
    POSITIVE LOGITS
     baby
    0.15
    ahn
    0.15
     Erg
    0.15
    ainen
    0.14
     Every
    0.14
    оÑĢÑĤ
    0.14
    ici
    0.14
     erg
    0.14
    icit
    0.14
     Hog
    0.13
    Act Density 0.016%

    No Known Activations