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

    Neuronpedia

    INDEX
    Explanations

    verbs related to shuffling or moving items around

    oai_token-act-pair · gpt-3.5-turbo

    actions or behaviors associated with movement or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    USE
    -0.73
     pity
    -0.71
     fixation
    -0.68
     lapse
    -0.67
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    ãĤ´ãĥ³
    -0.66
     Âł Âł Âł Âł
    -0.65
     anten
    -0.64
    terday
    -0.63
    ãĥīãĥ©
    -0.61
    POSITIVE LOGITS
    les
    1.65
    led
    1.65
    lers
    1.58
    ling
    1.54
    ler
    1.36
    lin
    1.21
    leground
    1.11
    lement
    1.11
    lins
    1.11
    lies
    1.10
    Act Density 0.050%

    No Known Activations