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

    Neuronpedia

    INDEX
    Explanations

    commands and paths related to computer programming

    oai_token-act-pair · gpt-3.5-turbo

    technical symbols and command line syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     afore
    -0.75
     Cambridge
    -0.67
     mind
    -0.66
     Nieto
    -0.66
     Blackwell
    -0.64
     leading
    -0.64
     Shepard
    -0.64
     Springer
    -0.63
     minds
    -0.63
     Brow
    -0.62
    POSITIVE LOGITS
    rf
    1.17
    vv
    1.13
    export
    1.12
    nos
    1.11
    rw
    1.11
    verb
    1.09
    eq
    1.08
    force
    1.07
    shared
    1.07
    depth
    1.07
    Act Density 0.019%

    No Known Activations