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

    Neuronpedia

    INDEX
    Explanations

    words and variations related to "sign" or "signifying."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brain
    -0.16
    oucher
    -0.15
    ync
    -0.15
    ted
    -0.15
    imeline
    -0.15
    BOSE
    -0.15
    orts
    -0.15
    覧
    -0.15
     ìĭľíĸī
    -0.14
    stroy
    -0.14
    POSITIVE LOGITS
    ificantly
    0.27
    atures
    0.26
    ificance
    0.25
    alled
    0.23
    ificant
    0.22
    SIGN
    0.21
    atories
    0.20
    aling
    0.19
    post
    0.19
    /sign
    0.19
    Act Density 0.037%

    No Known Activations