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

    Neuronpedia

    INDEX
    Explanations

    references to audits and auditing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĥÑģÑĤ
    -0.17
    oha
    -0.15
    па
    -0.15
    .uml
    -0.14
     ham
    -0.14
    ej
    -0.14
    tere
    -0.14
    iol
    -0.14
    InOut
    -0.14
    rikes
    -0.14
    POSITIVE LOGITS
    LOSS
    0.15
    aye
    0.15
    robe
    0.15
    moz
    0.14
    defs
    0.14
    ably
    0.14
    orting
    0.14
    ayar
    0.14
     Material
    0.14
     atr
    0.14
    Act Density 0.005%

    No Known Activations