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

    Neuronpedia

    INDEX
    Explanations

    symbols and words related to science, fraud, and online communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ministers
    -0.14
    -generic
    -0.14
    .PropertyType
    -0.13
    ADOW
    -0.13
    adow
    -0.13
    óm
    -0.13
     Mess
    -0.13
     Ministry
    -0.13
    aight
    -0.13
    .Expressions
    -0.13
    POSITIVE LOGITS
     qu
    0.20
    Snake
    0.16
    &q
    0.16
     .↵↵
    0.15
     pseud
    0.15
     woo
    0.15
    (qu
    0.15
     snake
    0.15
     Snake
    0.14
     placebo
    0.14
    Act Density 0.003%

    No Known Activations