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

    Neuronpedia

    INDEX
    Explanations

    language related to threats and intimidation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittel
    -0.16
    ENDED
    -0.15
    esel
    -0.15
    yme
    -0.14
    aná
    -0.14
    iban
    -0.14
    obe
    -0.14
    otten
    -0.14
    .oracle
    -0.14
    -spe
    -0.14
    POSITIVE LOGITS
    -threat
    0.16
     threatens
    0.15
     threatened
    0.15
    -toggler
    0.15
     threats
    0.15
    addock
    0.15
    gas
    0.14
     intimid
    0.14
    ingly
    0.14
     threatening
    0.14
    Act Density 0.064%

    No Known Activations