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

    Neuronpedia

    INDEX
    Explanations

    references to ninjas and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RuntimeObject
    -0.17
     sac
    -0.15
    vatel
    -0.15
    imers
    -0.15
    quirer
    -0.15
    umont
    -0.14
    [System
    -0.14
    lessly
    -0.14
    kaar
    -0.14
    nown
    -0.13
    POSITIVE LOGITS
    -like
    0.19
    like
    0.16
    ie
    0.16
    inh
    0.15
    iform
    0.15
    gram
    0.14
    oes
    0.14
    isch
    0.14
    elib
    0.14
    ic
    0.13
    Act Density 0.080%

    No Known Activations