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

    Neuronpedia

    INDEX
    Explanations

    terms related to options and opt-out mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldon
    -0.17
    ionage
    -0.16
    ignum
    -0.15
    jvu
    -0.15
    ÑĢÑĥÑģ
    -0.15
    .ease
    -0.15
    elsey
    -0.14
    processable
    -0.14
    readcr
    -0.14
    ingham
    -0.14
    POSITIVE LOGITS
     Klo
    0.17
    ziel
    0.17
     related
    0.14
     magnesium
    0.14
     standards
    0.14
     standard
    0.14
    ubb
    0.14
     Perr
    0.14
     op
    0.14
     fore
    0.14
    Act Density 0.015%

    No Known Activations