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

    Neuronpedia

    INDEX
    Explanations

    words related to direction and straightforward actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or processes, particularly those suggesting forward movement or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¶
    -0.75
    aretz
    -0.70
    å£
    -0.69
    ischer
    -0.68
    inea
    -0.66
    INS
    -0.66
    NSA
    -0.66
    ISON
    -0.65
    ieri
    -0.64
    Ñı
    -0.63
    POSITIVE LOGITS
     chronological
    0.73
     quart
    0.70
    theless
    0.69
     mean
    0.62
     brill
    0.62
     ur
    0.61
    usterity
    0.61
    ttle
    0.60
     tar
    0.60
     caste
    0.59
    Act Density 0.198%

    No Known Activations