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

    Neuronpedia

    INDEX
    Explanations

    references to software artifacts and dependencies in code configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    subclass
    -0.15
     discrimin
    -0.15
    enuity
    -0.14
    Äįet
    -0.14
    ered
    -0.14
     iddi
    -0.14
    erin
    -0.14
    ochen
    -0.14
    onom
    -0.14
    ilon
    -0.14
    POSITIVE LOGITS
    Lite
    0.15
    iry
    0.15
    INUX
    0.14
    ACHER
    0.14
    Å¡ov
    0.14
    sto
    0.13
    _hosts
    0.13
    anga
    0.13
    atos
    0.13
     à¤īल
    0.13
    Act Density 0.006%

    No Known Activations