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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to signals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reh
    -0.17
    ër
    -0.17
    enga
    -0.16
    istry
    -0.16
    erty
    -0.16
    ilet
    -0.16
    esi
    -0.15
    falls
    -0.15
    àµįà´
    -0.15
    angles
    -0.15
    POSITIVE LOGITS
    .SIG
    0.26
    (SIG
    0.22
    _strength
    0.19
    étique
    0.19
     strength
    0.18
    geber
    0.18
    ificantly
    0.18
    ificance
    0.17
    ourney
    0.16
    .Signal
    0.16
    Act Density 0.013%

    No Known Activations