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

    Neuronpedia

    INDEX
    Explanations

    references to user profiles or profiling processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    est
    -0.17
    że
    -0.15
    اتر
    -0.15
    ibold
    -0.15
    la
    -0.15
    rer
    -0.15
    iest
    -0.15
     оÑĩевид
    -0.15
    /free
    -0.15
    estre
    -0.14
    POSITIVE LOGITS
    led
    0.21
    /profile
    0.21
    tte
    0.18
    him
    0.16
    -specific
    0.16
    urum
    0.15
    /class
    0.15
    sig
    0.15
    contres
    0.14
    sm
    0.14
    Act Density 0.014%

    No Known Activations