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

    Neuronpedia

    INDEX
    Explanations

    information about something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to acquiring information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sabha
    -0.77
    ĸļ
    -0.69
    1969
    -0.68
    ħĭ
    -0.68
    OGR
    -0.67
    meter
    -0.67
     photoc
    -0.66
    opic
    -0.66
    mouth
    -0.66
    gam
    -0.64
    POSITIVE LOGITS
     how
    0.74
     topics
    0.73
     why
    0.72
    andise
    0.68
     specifics
    0.68
     whats
    0.67
     NX
    0.66
    leaf
    0.66
     setting
    0.66
     this
    0.63
    Act Density 0.096%

    No Known Activations