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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and user experience

    oai_token-act-pair · gpt-3.5-turbo

    expressions of social interaction or public sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.73
     stabilization
    -0.70
     forfeiture
    -0.70
    INAL
    -0.70
     surrog
    -0.68
     inclusive
    -0.66
     qualitative
    -0.62
    stress
    -0.61
     challeng
    -0.61
     preparation
    -0.61
    POSITIVE LOGITS
     whom
    0.93
    hirt
    0.90
    who
    0.90
     rejoice
    0.79
     who
    0.75
    whose
    0.75
    semble
    0.70
    hips
    0.67
    itans
    0.66
    hip
    0.66
    Act Density 0.938%

    No Known Activations