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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news events or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     bene
    -0.65
     brim
    -0.64
     omission
    -0.60
     Detected
    -0.58
     absence
    -0.55
     silhou
    -0.55
    lication
    -0.55
     Glob
    -0.54
     inval
    -0.53
     annex
    -0.53
    POSITIVE LOGITS
    touch
    0.96
     trouble
    0.82
    Touch
    0.79
    retty
    0.76
     touch
    0.72
    itialized
    0.72
     grips
    0.71
    way
    0.70
    offensive
    0.70
    ked
    0.69
    Act Density 0.115%

    No Known Activations