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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods, particularly the first days, weeks, and years of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rust
    -0.68
    redict
    -0.64
    rompt
    -0.64
    ãĥ¤
    -0.63
    ateg
    -0.62
    zsche
    -0.61
    athy
    -0.59
    atility
    -0.59
    ortium
    -0.58
    ictive
    -0.57
    POSITIVE LOGITS
     of
    0.96
    of
    0.76
     onwards
    0.75
    Of
    0.75
    akedown
    0.75
    nings
    0.73
    endment
    0.73
     thereof
    0.71
     alone
    0.69
     Of
    0.68
    Act Density 0.074%

    No Known Activations