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

    Neuronpedia

    INDEX
    Explanations

    percentage values in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    percentage symbols and associated numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compr
    -0.80
     exerc
    -0.74
    ITED
    -0.74
     hypert
    -0.64
     convened
    -0.62
     accompanied
    -0.62
    issued
    -0.61
     issued
    -0.61
     Rav
    -0.60
     informed
    -0.60
    POSITIVE LOGITS
    %%%%
    0.87
    AppData
    0.86
    -+
    0.81
    username
    0.78
    files
    0.78
    steamapps
    0.75
    esi
    0.73
    ll
    0.72
    rax
    0.72
    acre
    0.71
    Act Density 0.020%

    No Known Activations