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

    Neuronpedia

    INDEX
    Explanations

    names and specific terms related to characters or entities within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.77
    ¯¯¯¯
    -0.77
    ãģ®éŃĶ
    -0.77
    ¯¯
    -0.72
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.71
    ndra
    -0.69
     faint
    -0.69
    ĪĴ
    -0.69
    perature
    -0.69
    Else
    -0.68
    POSITIVE LOGITS
    hod
    1.00
    rolet
    0.96
    opa
    0.95
    ozo
    0.91
    oton
    0.89
    aza
    0.89
    dos
    0.88
    uid
    0.88
    ados
    0.85
    uri
    0.85
    Act Density 0.006%

    No Known Activations