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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "idea" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucha
    -0.16
    endon
    -0.16
    BSD
    -0.15
    dess
    -0.15
    our
    -0.15
    ir
    -0.15
    imes
    -0.14
    conj
    -0.14
    ello
    -0.14
    don
    -0.14
    POSITIVE LOGITS
    ohn
    0.15
    istic
    0.15
    aida
    0.15
    ative
    0.15
    ually
    0.14
    beh
    0.14
    istically
    0.14
    .idea
    0.14
     behind
    0.14
    epoch
    0.14
    Act Density 0.049%

    No Known Activations