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

    Neuronpedia

    INDEX
    Explanations

    connections to conditional phrases and qualifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ments
    -0.17
    gars
    -0.16
    issing
    -0.16
    Jvm
    -0.16
    ileged
    -0.16
    pane
    -0.15
    ncy
    -0.14
    Foreign
    -0.14
    æķ·
    -0.14
    Aqu
    -0.14
    POSITIVE LOGITS
    ipt
    0.18
    oran
    0.17
    aylor
    0.16
    оба
    0.15
    lyph
    0.15
    orent
    0.15
     Dunk
    0.14
    awei
    0.14
     proof
    0.13
     çĶŁåij½åij¨æľŁåĩ½æķ°
    0.13
    Act Density 0.015%

    No Known Activations