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

    Neuronpedia

    INDEX
    Explanations

    themes of regret and personal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekl
    -0.17
    prise
    -0.16
    cak
    -0.16
    建
    -0.16
    guard
    -0.15
    ò
    -0.15
    iox
    -0.15
    _variation
    -0.14
    _GATE
    -0.14
    _singular
    -0.14
    POSITIVE LOGITS
    令
    0.17
    γκα
    0.16
    aban
    0.15
    ubo
    0.15
    neau
    0.15
    ys
    0.14
     Briggs
    0.14
     Sul
    0.14
    172
    0.13
     cle
    0.13
    Act Density 0.238%

    No Known Activations