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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conversational cues in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.84
    tagHelperRunner
    -0.75
    DockStyle
    -0.70
     Houſe
    -0.65
     Anſ
    -0.62
     becauſe
    -0.61
     myſelf
    -0.61
    abestanden
    -0.61
     समीक्षाएं
    -0.60
    NAG
    -0.59
    POSITIVE LOGITS
    ↵↵
    0.95
    UnusedPrivate
    0.70
    <eos>
    0.61
    说着
    0.60
    }];
    0.55
    }}/>
    0.54
    ↵↵↵
    0.54
    .”
    0.52
    .*")]
    0.52
    pinch
    0.51
    Act Density 0.050%

    No Known Activations