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

    Neuronpedia

    INDEX
    Explanations

    terms related to official designations or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilities
    -0.15
    iná
    -0.14
    ubat
    -0.14
    FPS
    -0.13
    DST
    -0.13
     blanks
    -0.13
     pul
    -0.13
    ermann
    -0.13
    acco
    -0.13
    Ñīе
    -0.13
    POSITIVE LOGITS
    aldi
    0.18
    .scalablytyped
    0.16
    erus
    0.15
    µ
    0.14
    ephir
    0.14
    thern
    0.14
    estruction
    0.14
    _vlog
    0.14
    ×ķ
    0.14
    irl
    0.14
    Act Density 0.011%

    No Known Activations