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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing contrasting information

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAST
    -0.74
    ESA
    -0.73
    tainment
    -0.71
    teen
    -0.70
    rain
    -0.69
    BAT
    -0.67
    AGE
    -0.67
    air
    -0.67
    aline
    -0.66
    asures
    -0.66
    POSITIVE LOGITS
     contrast
    1.05
     conjunction
    0.89
     turn
    0.86
     particular
    0.86
     collaboration
    0.81
     contrad
    0.80
     cooperation
    0.80
     whom
    0.79
     consultation
    0.78
     exception
    0.75
    Act Density 0.118%

    No Known Activations