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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statements or arguments

    oai_token-act-pair · gpt-3.5-turbo

    statements and claims made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.82
    odcast
    -0.79
    ocl
    -0.75
    enum
    -0.72
    uminati
    -0.69
    iership
    -0.69
    peg
    -0.69
    transfer
    -0.69
    iffe
    -0.68
    avorite
    -0.68
    POSITIVE LOGITS
     "[
    0.86
     it
    0.84
     they
    0.80
     instead
    0.78
     "'
    0.78
     therein
    0.75
     "...
    0.73
     that
    0.72
     "(
    0.72
     '[
    0.71
    Act Density 0.085%

    No Known Activations