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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating curiosity or doubt

    oai_token-act-pair · gpt-3.5-turbo

    expressions of curiosity or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onica
    -0.56
    rites
    -0.55
    ONG
    -0.55
    itual
    -0.55
    oided
    -0.54
    ortunately
    -0.54
    orest
    -0.53
    legates
    -0.51
    uctions
    -0.51
    absor
    -0.50
    POSITIVE LOGITS
     aloud
    1.42
     why
    1.41
     whether
    1.31
    why
    1.29
     WHY
    1.29
     how
    1.25
     if
    1.12
    whether
    1.09
     HOW
    1.06
    how
    1.02
    Act Density 0.043%

    No Known Activations