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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a need or obligation to take a particular action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pires
    -0.79
     Glad
    -0.66
     Loud
    -0.60
     Compass
    -0.59
     Emerging
    -0.59
     Cah
    -0.59
     POV
    -0.58
     Bast
    -0.57
    Recommended
    -0.57
     Camb
    -0.57
    POSITIVE LOGITS
     wait
    1.03
     rethink
    1.02
     revise
    0.93
     settle
    0.85
     reconsider
    0.84
     revisit
    0.83
     waive
    0.82
     fend
    0.81
     abide
    0.79
     borrow
    0.76
    Act Density 0.103%

    No Known Activations