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

    Neuronpedia

    INDEX
    Explanations

    words related to the themes of identity and representation in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compact
    -0.16
    wargs
    -0.16
    nown
    -0.15
    aws
    -0.14
     Compact
    -0.14
    ãĥ³ãĥĶ
    -0.13
     gravity
    -0.13
    utral
    -0.13
    ìĸij
    -0.13
     miss
    -0.13
    POSITIVE LOGITS
    elige
    0.16
    .synthetic
    0.16
    XD
    0.15
    yš
    0.15
     åĽ
    0.14
    strup
    0.14
    tat
    0.14
    адж
    0.14
    resse
    0.14
     OSD
    0.14
    Act Density 0.063%

    No Known Activations