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

    Neuronpedia

    INDEX
    Explanations

    instances of subjective descriptions and evaluative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.17
    dou
    -0.15
    vise
    -0.15
     preamble
    -0.14
    iets
    -0.14
     Kendrick
    -0.14
    spm
    -0.14
    ongan
    -0.14
    stå
    -0.14
    stance
    -0.13
    POSITIVE LOGITS
    idon
    0.15
    adesh
    0.15
    inson
    0.15
    .strict
    0.15
    iji
    0.15
    ÃĹ↵↵
    0.14
    umb
    0.14
    á»±c
    0.14
    »
    0.14
    amel
    0.13
    Act Density 0.100%

    No Known Activations