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

    Neuronpedia

    INDEX
    Explanations

    code snippets or programming syntax

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.92
    orate
    -0.78
    ishly
    -0.78
    bett
    -0.76
    ille
    -0.74
    arer
    -0.73
    uve
    -0.73
    ellery
    -0.72
    Reilly
    -0.71
    Lex
    -0.70
    POSITIVE LOGITS
    ::::::::
    0.90
    *:
    0.81
     ???
    0.69
    :{
    0.68
     Ritual
    0.62
    ,,,,,,,,
    0.61
    775
    0.61
     Anyone
    0.61
     Unknown
    0.60
     Âł Âł Âł Âł
    0.60
    Act Density 0.020%

    No Known Activations