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

    Neuronpedia

    INDEX
    Explanations

    actions or activities performed by individuals in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to various activities and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥķãĤ©
    -0.71
    ãĤ±
    -0.71
    éĹ
    -0.70
    ãĥ´ãĤ¡
    -0.70
    é¾įå¥ij士
    -0.69
    女
    -0.66
    berus
    -0.64
    %%%%
    -0.64
    sama
    -0.63
     counterpart
    -0.63
    POSITIVE LOGITS
     themselves
    1.02
     their
    0.83
     theirs
    0.78
     alike
    0.76
     freely
    0.76
    iscover
    0.73
     THEIR
    0.71
     spontaneously
    0.69
     blindly
    0.65
    ingly
    0.64
    Act Density 0.439%

    No Known Activations