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

    Neuronpedia

    INDEX
    Explanations

    instances of negative scrutiny or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increased scrutiny or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sake
    -0.68
     Begins
    -0.67
     cures
    -0.63
     Potion
    -0.62
     dwarves
    -0.62
     caves
    -0.60
     Meridian
    -0.58
     Journals
    -0.58
     apes
    -0.57
    ents
    -0.57
    POSITIVE LOGITS
     scrutiny
    1.21
    whel
    0.89
     criticism
    0.89
     suspicion
    0.87
     fire
    0.85
     pressure
    0.83
     attention
    0.83
     tremend
    0.82
     scanner
    0.82
     brunt
    0.81
    Act Density 0.039%

    No Known Activations