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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values or statistics related to quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DNEY
    -0.38
    ❯
    -0.36
    InjectAttribute
    -0.33
     PhpStorm
    -0.32
    Étymologie
    -0.32
    cirq
    -0.31
    BagConstraints
    -0.30
     fan
    -0.30
    OCCURRED
    -0.30
    genheim
    -0.30
    POSITIVE LOGITS
    0
    0.72
     חיצוניים
    0.62
    ſelves
    0.57
     étoient
    0.53
     avoient
    0.53
     BoxFit
    0.53
     feroit
    0.52
     pouvoit
    0.51
    ۰۰
    0.50
     themſelves
    0.49
    Act Density 0.328%

    No Known Activations