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

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and expressions involving processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £
    -0.15
    XL
    -0.15
     reform
    -0.15
    erin
    -0.15
    er
    -0.14
    .rot
    -0.14
     latter
    -0.14
    lh
    -0.14
    _TEMPLATE
    -0.14
     ngang
    -0.14
    POSITIVE LOGITS
    atatype
    0.18
    reesome
    0.17
    ichert
    0.16
    elop
    0.15
    881
    0.15
    eland
    0.15
    νοÏį
    0.15
    ActionCreators
    0.14
    oser
    0.14
    udy
    0.14
    Act Density 0.172%

    No Known Activations