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

    Neuronpedia

    INDEX
    Explanations

    perceived concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    references to perceptions or beliefs about situations and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etts
    -0.81
    istration
    -0.74
    akura
    -0.73
    raid
    -0.73
    kers
    -0.73
    hire
    -0.71
    packed
    -0.70
    unny
    -0.69
    ercise
    -0.68
    driver
    -0.68
    POSITIVE LOGITS
     conflic
    0.89
     perceptions
    0.84
     recoil
    0.83
    wcsstore
    0.82
     metic
    0.79
     cumbers
    0.79
     attractiveness
    0.77
     animosity
    0.74
    TI
    0.74
     hostility
    0.71
    Act Density 0.027%

    No Known Activations