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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intensity or urgency

    oai_token-act-pair · gpt-3.5-turbo

    an unusual character or symbol in the text that may indicate formatting or error

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matic
    -0.95
    urated
    -0.84
    raints
    -0.82
    writers
    -0.80
     primates
    -0.75
     similarities
    -0.71
    igators
    -0.70
    orial
    -0.69
    engers
    -0.69
     Instr
    -0.69
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.23
    ľ
    1.02
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.02
    à©
    1.01
    ĺ
    0.97
    ĸ
    0.95
    ::::::::
    0.94
    Ķ
    0.94
    Ĺ
    0.94
    Ĩ
    0.93
    Act Density 0.156%

    No Known Activations