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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "some" is followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditional or variable scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppable
    -0.79
    ifax
    -0.73
    ideo
    -0.70
    rogens
    -0.68
    redit
    -0.67
    oki
    -0.67
    âĢİ
    -0.67
    aque
    -0.67
    ailable
    -0.67
    ilant
    -0.66
    POSITIVE LOGITS
     guise
    0.95
     cases
    0.94
     respects
    0.90
     workplaces
    0.89
     manner
    0.88
     areas
    0.87
     regions
    0.86
     contexts
    0.86
     households
    0.84
     jurisdictions
    0.81
    Act Density 0.114%

    No Known Activations