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

    Neuronpedia

    INDEX
    Explanations

    phrases related to behavioral aspects and effects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to behavioral sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eous
    -1.01
    smanship
    -0.82
    shall
    -0.82
    enthal
    -0.76
    worthy
    -0.74
    zzo
    -0.73
    cake
    -0.73
    bur
    -0.73
    urat
    -0.72
    eem
    -0.72
    POSITIVE LOGITS
    avior
    1.18
     behavioral
    1.01
     behavi
    0.95
    aviour
    0.88
     behavioural
    0.86
     Behavioral
    0.85
     biologists
    0.85
     modification
    0.84
     genetics
    0.82
     conditioning
    0.82
    Act Density 0.021%

    No Known Activations