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

    Neuronpedia

    INDEX
    Explanations

    the preposition "in" paired with a verb or noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate being involved or engaged in various situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bene
    -0.67
     indicating
    -0.60
     coron
    -0.59
     testament
    -0.59
    Brand
    -0.57
     POL
    -0.57
    ICA
    -0.56
     omission
    -0.56
     brim
    -0.55
     Else
    -0.55
    POSITIVE LOGITS
     touch
    1.11
     trouble
    1.11
    touch
    0.94
    ked
    0.90
     Touch
    0.87
    Touch
    0.85
    itialized
    0.80
     bed
    0.80
     grips
    0.78
     shape
    0.75
    Act Density 0.060%

    No Known Activations