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

    Neuronpedia

    INDEX
    Explanations

    words related to exaggeration or intensity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "hyper."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivity
    -0.79
    ello
    -0.75
    oured
    -0.73
    Ú
    -0.72
    UE
    -0.72
     Continued
    -0.71
    uary
    -0.71
    eous
    -0.70
     Rite
    -0.70
    dylib
    -0.69
    POSITIVE LOGITS
    visor
    1.12
     hyper
    1.09
    bole
    1.08
     hyp
    0.96
    hyper
    0.92
    visors
    0.87
    dimension
    0.86
    tro
    0.86
    hyp
    0.85
    bol
    0.85
    Act Density 0.007%

    No Known Activations