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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     think
    -0.58
    getItemId
    -0.54
     generation
    -0.51
    uszka
    -0.51
    Gambas
    -0.50
     involve
    -0.49
     شر
    -0.49
    stag
    -0.47
     dates
    -0.47
    ways
    -0.46
    POSITIVE LOGITS
    CodedInputStream
    0.70
    ImageContext
    0.69
    mergeFrom
    0.67
     TestBed
    0.66
    ScopeManager
    0.65
    openConnection
    0.63
    quelize
    0.61
    Hentet
    0.60
    parsedMessage
    0.59
    newArrayList
    0.59
    Act Density 0.363%

    No Known Activations