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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.79
    amic
    -0.63
    eding
    -0.63
    icol
    -0.62
    cler
    -0.61
    SPONSORED
    -0.61
    cript
    -0.61
    iverpool
    -0.61
    gren
    -0.60
    ulty
    -0.59
    POSITIVE LOGITS
    reprene
    0.83
     revenge
    0.72
     everybody
    0.67
    urities
    0.66
     everyone
    0.65
     answers
    0.65
     to
    0.64
     assurances
    0.64
    anta
    0.62
    ACY
    0.62
    Act Density 0.077%

    No Known Activations