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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating exclusion or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elda
    -0.17
    uset
    -0.15
     Hass
    -0.15
    å¡ij
    -0.14
    ourg
    -0.14
     اÙĦزر
    -0.14
    spender
    -0.14
     बर
    -0.14
    ProgressHUD
    -0.14
    885
    -0.14
    POSITIVE LOGITS
    ria
    0.16
    ua
    0.15
    inine
    0.15
    Tro
    0.15
     Lay
    0.14
    idebar
    0.14
     Tro
    0.14
     hun
    0.14
     waters
    0.14
    RIA
    0.14
    Act Density 0.006%

    No Known Activations