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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts or ideas that require contemplation or consideration

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to thoughts and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilver
    -0.70
    NetMessage
    -0.66
    henko
    -0.62
    iaries
    -0.61
    hops
    -0.60
    KO
    -0.60
    pec
    -0.58
     Frag
    -0.58
    otted
    -0.58
    osponsors
    -0.58
    POSITIVE LOGITS
     itself
    0.86
    ultimate
    0.83
    iest
    0.80
    osphere
    0.71
    antry
    0.71
    fulness
    0.67
     anew
    0.64
    UTH
    0.62
     altogether
    0.61
    ariat
    0.60
    Act Density 0.344%

    No Known Activations