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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or desire to engage in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usal
    -0.18
    acias
    -0.14
    hiro
    -0.14
    elah
    -0.14
    UMMY
    -0.14
    resi
    -0.13
    ãĢħ
    -0.13
    éī
    -0.13
    sono
    -0.13
    ä¼į
    -0.13
    POSITIVE LOGITS
    @class
    0.16
    anz
    0.15
    497
    0.15
    onomy
    0.15
    afari
    0.14
    ÃĹ↵↵
    0.14
    iske
    0.14
    ekl
    0.14
    xr
    0.13
    nton
    0.13
    Act Density 0.087%

    No Known Activations