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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions or events happening in the future

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or conditions related to technology and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.68
    toggle
    -0.60
    ][/
    -0.59
    oway
    -0.58
    ticket
    -0.56
    picture
    -0.56
    itus
    -0.55
    andum
    -0.53
    venth
    -0.51
    avid
    -0.51
    POSITIVE LOGITS
     raining
    0.95
     impossible
    0.62
     easier
    0.54
     Tradable
    0.53
    ãĥķãĤ©
    0.50
     easy
    0.50
     reopened
    0.50
     unclear
    0.49
     Pwr
    0.49
     abundantly
    0.49
    Act Density 0.791%

    No Known Activations