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

    Neuronpedia

    INDEX
    Explanations

    words related to certainty or emphasis, such as "irrefutable" or "definitely"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "ir-" indicating negation or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzo
    -0.81
     guiActiveUnfocused
    -0.81
    soDeliveryDate
    -0.76
     Parad
    -0.72
    hetti
    -0.72
     Opera
    -0.69
     Vinyl
    -0.69
     Remastered
    -0.68
    ership
    -0.68
    uyomi
    -0.67
    POSITIVE LOGITS
    cles
    1.04
    idium
    0.94
    ked
    0.93
    acet
    0.85
    ilateral
    0.83
    respons
    0.82
    respective
    0.78
    itably
    0.75
    religious
    0.75
    acial
    0.74
    Act Density 0.007%

    No Known Activations