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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating permission or possibility

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "may" indicating possibility or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ging
    -0.88
     Fighter
    -0.74
    hran
    -0.70
    ocracy
    -0.70
    ged
    -0.68
    cheon
    -0.66
     Composite
    -0.66
    ãĥ¼ãĥ«
    -0.64
    masters
    -0.63
     Dirty
    -0.63
    POSITIVE LOGITS
    hap
    0.98
    haps
    0.96
    onna
    0.92
     optionally
    0.91
     be
    0.87
    entimes
    0.87
     confuse
    0.82
     derive
    0.80
     alternatively
    0.80
    adian
    0.79
    Act Density 0.070%

    No Known Activations