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

    Neuronpedia

    INDEX
    Explanations

    programming or technical commands enclosed in symbols like '>' and numbers

    oai_token-act-pair · gpt-3.5-turbo

    section headers or navigational cues in instructional or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.95
    ModLoader
    -0.93
    onial
    -0.90
    etheless
    -0.89
    erville
    -0.85
    teenth
    -0.85
    yssey
    -0.84
    iqueness
    -0.83
    acies
    -0.81
    hement
    -0.81
    POSITIVE LOGITS
    _>
    1.22
    =>
    0.84
    ++++
    0.82
     >
    0.76
    .<
    0.75
     Dangerous
    0.69
     Preferences
    0.66
    tf
    0.66
     (<
    0.65
    >>>>
    0.65
    Act Density 0.014%

    No Known Activations