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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opp
    -0.14
    vv
    -0.13
     Danger
    -0.13
    fasta
    -0.13
     Bernard
    -0.13
    .isEnabled
    -0.13
     NB
    -0.13
    åŁ
    -0.13
     Lust
    -0.13
     Gas
    -0.13
    POSITIVE LOGITS
    ово
    0.16
    ventus
    0.15
    illos
    0.15
    деÑĤ
    0.15
    criptor
    0.15
    gota
    0.14
    eview
    0.14
    entin
    0.14
    967
    0.14
    ideos
    0.13
    Act Density 0.027%

    No Known Activations