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

    Neuronpedia

    INDEX
    Explanations

    verbs related to communicating specific information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a lack of specification or detail about information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tumblr
    -0.74
    assic
    -0.70
    imum
    -0.69
    itton
    -0.68
    Throw
    -0.68
    edom
    -0.66
    bey
    -0.65
    irt
    -0.65
    twitch
    -0.64
    aturated
    -0.63
    POSITIVE LOGITS
     specifics
    1.42
     nor
    1.00
     details
    0.97
     anything
    0.95
     specific
    0.94
     particulars
    0.91
     any
    0.86
     anymore
    0.86
     publicly
    0.85
     disclosing
    0.85
    Act Density 0.172%

    No Known Activations