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

    Neuronpedia

    INDEX
    Explanations

    nouns and significant terms related to community and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.16
    ippers
    -0.15
    uld
    -0.14
     children
    -0.14
    ł
    -0.14
    patches
    -0.14
     kids
    -0.13
     invers
    -0.13
    ahir
    -0.13
    asename
    -0.13
    POSITIVE LOGITS
    ctal
    0.17
    çī§
    0.16
    esiz
    0.15
    å¯
    0.15
    rape
    0.15
    lay
    0.15
    opa
    0.14
    ONG
    0.14
    posta
    0.14
    estro
    0.14
    Act Density 0.003%

    No Known Activations