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

    Neuronpedia

    INDEX
    Explanations

    terms related to manipulation and manipulative behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    068
    -0.17
    phant
    -0.16
    åı·
    -0.15
    ighted
    -0.15
    bie
    -0.15
     Ñģамое
    -0.14
    WISE
    -0.14
    اÙĦد
    -0.14
    stp
    -0.14
    367
    -0.14
    POSITIVE LOGITS
    uela
    0.23
    hattan
    0.21
    ually
    0.21
    ual
    0.21
    tras
    0.21
    (man
    0.21
    ifold
    0.20
    uelle
    0.20
    iac
    0.19
    uales
    0.19
    Act Density 0.048%

    No Known Activations