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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     closest
    -0.19
     nearest
    -0.19
     encount
    -0.16
     close
    -0.15
     CLOSE
    -0.14
    closest
    -0.14
    ={({
    -0.14
    urga
    -0.14
    same
    -0.14
    ضÙĪ
    -0.14
    POSITIVE LOGITS
    Remaining
    0.28
     remaining
    0.28
     Remaining
    0.27
    åī©
    0.26
    remaining
    0.26
     remainder
    0.24
    remainder
    0.23
    _remaining
    0.21
     zby
    0.20
     åī
    0.20
    Act Density 0.185%

    No Known Activations