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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connectors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä»®
    -0.16
    eh
    -0.15
    opathic
    -0.14
    zsche
    -0.14
     Meet
    -0.14
    atars
    -0.13
     Angle
    -0.13
    ávÄĽ
    -0.13
    als
    -0.13
    arget
    -0.13
    POSITIVE LOGITS
    ì¶ľ
    0.15
    寸
    0.15
    rock
    0.14
     æ¥
    0.14
    elo
    0.14
     Maxwell
    0.14
    ERO
    0.13
    wards
    0.13
    .Cos
    0.13
    Invariant
    0.13
    Act Density 0.005%

    No Known Activations