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

    Neuronpedia

    INDEX
    Explanations

    modals indicating possibility or necessity

    oai_token-act-pair · gpt-3.5-turbo

    negations and conditional phrases related to hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isively
    -0.81
    pick
    -0.66
    wards
    -0.64
    perty
    -0.62
    cius
    -0.61
    izens
    -0.61
    izen
    -0.61
    luaj
    -0.59
    orously
    -0.58
    ngth
    -0.58
    POSITIVE LOGITS
    soType
    0.71
    OTAL
    0.68
    rue
    0.66
     GOODMAN
    0.64
    SPONSORED
    0.64
    GD
    0.64
     happening
    0.63
     Bungie
    0.63
    ãĥķãĤ©
    0.63
     happ
    0.63
    Act Density 0.169%

    No Known Activations