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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey statements or quotes made by individuals, particularly in a formal or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unce
    -0.14
    decltype
    -0.14
    iece
    -0.14
    оже
    -0.14
    otel
    -0.13
     GRAT
    -0.13
    eparator
    -0.13
    akis
    -0.13
    essler
    -0.13
     Alarm
    -0.13
    POSITIVE LOGITS
     spokesman
    0.62
     spokesperson
    0.58
     spokeswoman
    0.54
     spokes
    0.52
     statement
    0.44
     Sp
    0.38
     representative
    0.36
     press
    0.35
    statement
    0.33
    Sp
    0.32
    Act Density 0.133%

    No Known Activations