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

    Neuronpedia

    INDEX
    Explanations

    keywords related to modeling and analysis within scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ead
    -0.15
    toFloat
    -0.14
     Bold
    -0.14
    igm
    -0.14
    igan
    -0.14
    ansen
    -0.14
    uther
    -0.13
    alara
    -0.13
    ãĥ¼ãĥĪ
    -0.13
    ajan
    -0.13
    POSITIVE LOGITS
    ding
    0.25
    elling
    0.23
    ded
    0.21
     mod
    0.20
    ality
    0.19
     Mod
    0.19
    abbo
    0.18
    eller
    0.18
    esty
    0.18
    (mod
    0.17
    Act Density 0.015%

    No Known Activations