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

    Neuronpedia

    INDEX
    Explanations

    personal reflections and expressions of self-identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atsu
    -0.16
    amen
    -0.15
    abella
    -0.14
    ÅĤe
    -0.14
    ardo
    -0.14
    apr
    -0.14
    æ¡Ī
    -0.13
    ander
    -0.13
    imus
    -0.13
    igo
    -0.13
    POSITIVE LOGITS
     gros
    0.15
    tas
    0.15
     also
    0.15
     Crosby
    0.15
    tower
    0.14
    ¥
    0.14
     také
    0.14
    #echo
    0.14
    alic
    0.14
    ilers
    0.14
    Act Density 0.211%

    No Known Activations