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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to experimental measurements and physical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampo
    -0.18
    bern
    -0.17
    aeda
    -0.15
    argin
    -0.15
    á»ijc
    -0.15
    unic
    -0.15
    kers
    -0.14
    ekler
    -0.14
    æĺĮ
    -0.14
    anchors
    -0.14
    POSITIVE LOGITS
    pow
    0.20
     powder
    0.19
     cooling
    0.18
     Phon
    0.17
    ç²ī
    0.17
     Powder
    0.16
    Pow
    0.16
     temperature
    0.16
    bcc
    0.16
     cooled
    0.16
    Act Density 0.005%

    No Known Activations