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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web address structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     leaflets
    -0.82
     triangles
    -0.81
     shading
    -0.78
     Parables
    -0.76
     leaps
    -0.75
     dispel
    -0.73
     creep
    -0.73
     gearing
    -0.72
     ACTIONS
    -0.72
     stride
    -0.70
    POSITIVE LOGITS
    localhost
    1.86
    example
    1.67
    username
    1.49
    USER
    1.39
    foo
    1.36
    domain
    1.31
    xxxx
    1.29
    XXXX
    1.28
    admin
    1.28
    76561
    1.25
    Act Density 0.104%

    No Known Activations