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

    Neuronpedia

    INDEX
    Explanations

    words related to uninhabitable places

    oai_token-act-pair · gpt-3.5-turbo

    words related to habitation and living conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peel
    -0.69
     Stack
    -0.68
     Pikachu
    -0.64
     donations
    -0.63
     compliments
    -0.62
     whites
    -0.62
     RT
    -0.62
     opaque
    -0.61
     tip
    -0.61
     charges
    -0.60
    POSITIVE LOGITS
    hab
    4.89
    habi
    2.22
     Hab
    1.31
    hib
    1.21
    ha
    1.12
     Habit
    1.08
    hal
    1.08
    kef
    1.07
    hum
    1.07
    hy
    1.04
    Act Density 0.004%

    No Known Activations