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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unsolved issues or challenges

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "uns-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.79
    tsky
    -0.73
    zzo
    -0.73
     Grayson
    -0.71
    OPLE
    -0.69
     Guardians
    -0.69
     Mercury
    -0.68
    stanbul
    -0.68
     Panther
    -0.67
     Framework
    -0.67
    POSITIVE LOGITS
    rep
    1.00
    avour
    0.96
    uitive
    0.88
    alted
    0.87
    killed
    0.87
    heat
    0.86
    ident
    0.86
    apon
    0.84
    aved
    0.83
    oci
    0.83
    Act Density 0.005%

    No Known Activations