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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing skepticism or criticism in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑģÑĤи
    -0.15
    ç±
    -0.15
    aten
    -0.15
    uffy
    -0.15
    alu
    -0.15
    uci
    -0.15
     Osborne
    -0.14
    apol
    -0.14
    foy
    -0.14
     thụ
    -0.14
    POSITIVE LOGITS
    loe
    0.16
    ãĥªãĥ³
    0.16
     Package
    0.15
    =:
    0.14
    irs
    0.14
    instead
    0.14
    pow
    0.13
    ucher
    0.13
    ilate
    0.13
    ега
    0.13
    Act Density 0.214%

    No Known Activations