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

    Neuronpedia

    INDEX
    Explanations

    expressions that convey explanation or clarification of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anch
    -0.16
     Dun
    -0.16
    .mdl
    -0.15
    olo
    -0.15
    ether
    -0.15
    adden
    -0.15
    ua
    -0.15
    omp
    -0.14
    å¡
    -0.14
    ault
    -0.14
    POSITIVE LOGITS
    reesome
    0.18
    ovi
    0.15
    cta
    0.15
    кÑĥÑĤ
    0.15
    ritable
    0.15
    ilden
    0.14
    wind
    0.14
    elay
    0.14
    SED
    0.14
    istra
    0.14
    Act Density 0.135%

    No Known Activations