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

    Neuronpedia

    INDEX
    Explanations

    instances of persuasion or attempts to convince others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yms
    -0.16
    itler
    -0.16
    omb
    -0.16
    iet
    -0.15
    ookie
    -0.15
    uels
    -0.15
    instein
    -0.14
    lettes
    -0.14
    _PROGRAM
    -0.14
    ɵ
    -0.14
    POSITIVE LOGITS
     argument
    0.16
    316
    0.15
    atively
    0.15
    apore
    0.15
     args
    0.15
    ltk
    0.15
    ingly
    0.14
     (?)
    0.14
     convin
    0.14
     arg
    0.14
    Act Density 0.055%

    No Known Activations