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

    Neuronpedia

    INDEX
    Explanations

    related to manipulative or abusive behaviors in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %A
    -0.16
    UPPORTED
    -0.16
    537
    -0.15
    dej
    -0.15
    iry
    -0.15
     zero
    -0.14
    Lifetime
    -0.14
    nou
    -0.14
    å¬
    -0.14
    UCCEEDED
    -0.14
    POSITIVE LOGITS
    ÙĪÙĤت
    0.16
     Paras
    0.15
    yms
    0.15
    ook
    0.14
     cả
    0.14
    mos
    0.14
    :UIAlert
    0.14
    IPP
    0.14
    ŀæĢ§
    0.14
    AP
    0.13
    Act Density 0.055%

    No Known Activations