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

    Neuronpedia

    INDEX
    Explanations

    commands or prompts related to leaving comments or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rap
    -0.18
    ácil
    -0.16
    unas
    -0.15
    enga
    -0.15
     solicit
    -0.14
    /from
    -0.14
    ots
    -0.14
     diff
    -0.14
    mail
    -0.14
    .diff
    -0.14
    POSITIVE LOGITS
     behind
    0.20
     Behind
    0.19
    zá
    0.18
    lasting
    0.17
    orte
    0.17
    beck
    0.17
    afen
    0.17
    алÑĥ
    0.17
    Behind
    0.17
    beh
    0.16
    Act Density 0.035%

    No Known Activations