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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to details or specifics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to allocation, quantity, and resource distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igmatic
    -0.80
    eteen
    -0.73
    irteen
    -0.72
    èĢħ
    -0.67
    umerous
    -0.66
    acious
    -0.64
    idespread
    -0.63
    ixty
    -0.63
     ÂŃ
    -0.63
    founded
    -0.62
    POSITIVE LOGITS
     whats
    0.93
     CoC
    0.86
     them
    0.84
     pokemon
    0.84
     theirs
    0.83
     yours
    0.79
     ours
    0.79
     devs
    0.78
     stuff
    0.78
     ourselves
    0.75
    Act Density 1.020%

    No Known Activations