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

    Neuronpedia

    INDEX
    Explanations

    the word "still" in various contexts and sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey continuity or persistence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     elimination
    -0.73
    ASE
    -0.67
    insula
    -0.63
     Stim
    -0.62
    alties
    -0.62
     Relief
    -0.61
     Distribution
    -0.60
    Course
    -0.59
     Correction
    -0.59
     Moody
    -0.59
    POSITIVE LOGITS
    birth
    1.31
    born
    0.95
     exists
    0.86
    heres
    0.85
     intact
    0.84
     reeling
    0.82
     unanswered
    0.82
     retains
    0.80
     existed
    0.75
     manages
    0.74
    Act Density 0.061%

    No Known Activations