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

    Neuronpedia

    INDEX
    Explanations

    numerical calculations or equations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditional statements and the concept of obligation or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antioxid
    -0.93
    Balt
    -0.89
    natureconservancy
    -0.84
    GoldMagikarp
    -0.82
     behavi
    -0.81
    DAQ
    -0.75
    PDATE
    -0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.73
    CLASSIFIED
    -0.73
     adolesc
    -0.72
    POSITIVE LOGITS
    ividual
    0.90
    ogun
    0.71
    ecause
    0.71
    othal
    0.71
    itially
    0.71
    onga
    0.64
    irlf
    0.64
    ruary
    0.62
    initely
    0.61
     ItemLevel
    0.61
    Act Density 5.748%

    No Known Activations