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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or transfer from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    references to transitions or exchanges between different entities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lux
    -0.67
    BuyableInstoreAndOnline
    -0.65
    ª
    -0.64
    letters
    -0.64
    uci
    -0.64
    IK
    -0.63
    nit
    -0.61
    odore
    -0.60
     Motorsport
    -0.60
    cluded
    -0.60
    POSITIVE LOGITS
     depending
    0.94
    .
    0.84
    isphere
    0.82
     consecut
    0.80
    ciating
    0.75
    esthetic
    0.74
     vowel
    0.74
    stretched
    0.74
    ;
    0.73
     glance
    0.73
    Act Density 0.082%

    No Known Activations