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

    Neuronpedia

    INDEX
    Explanations

    decisions and actions that impact narratives or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.50
    #!/
    -0.48
    
    -0.47
    driver
    -0.46
    ędzynarod
    -0.45
     Driver
    -0.44
     driver
    -0.44
    enumii
    -0.43
    ?,?,
    -0.43
    }))
    -0.43
    POSITIVE LOGITS
     presence
    0.79
    presence
    0.73
     SwitchCompat
    0.72
     présence
    0.69
     Presence
    0.66
    Presence
    0.64
     aanwezig
    0.63
     CreateTagHelper
    0.60
     presencia
    0.60
     whenever
    0.60
    Act Density 0.347%

    No Known Activations