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

    Neuronpedia

    INDEX
    Explanations

    actions indicating physical force or conflict

    oai_token-act-pair · gpt-3.5-turbo

    actions related to restraint or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.76
     Dragonbound
    -0.74
     Deity
    -0.63
     Raider
    -0.62
     Sorceress
    -0.59
     Ideal
    -0.56
     objected
    -0.56
     Sloven
    -0.56
     Bruins
    -0.55
     Werner
    -0.55
    POSITIVE LOGITS
    ouncing
    1.37
    ping
    1.36
    icating
    1.31
    imating
    1.30
    ulating
    1.29
    reating
    1.29
    iting
    1.28
    iating
    1.25
    asuring
    1.23
    itting
    1.22
    Act Density 0.269%

    No Known Activations