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

    Neuronpedia

    INDEX
    Explanations

    Biblical references

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spir
    -0.78
     appropri
    -0.76
    olicy
    -0.73
     overhaul
    -0.71
     exacerb
    -0.71
     accrued
    -0.70
     overrun
    -0.69
     packing
    -0.69
     indu
    -0.69
     inund
    -0.68
    POSITIVE LOGITS
    Laughs
    1.64
    laughs
    1.57
    âĢ¦)
    1.48
    laughter
    1.24
    ...)
    1.23
    hide
    1.20
    emphasis
    1.17
    Note
    1.13
    Pause
    1.12
    laugh
    1.11
    Act Density 0.088%

    No Known Activations