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

    Neuronpedia

    INDEX
    Explanations

    strings enclosed in quotes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or special characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     experien
    -0.66
    agonist
    -0.65
    çĶ°
    -0.64
     capsule
    -0.62
    ocial
    -0.59
    Berry
    -0.59
    ICAN
    -0.59
    ivan
    -0.58
    Ń·
    -0.57
     attendance
    -0.56
    POSITIVE LOGITS
    ¯
    0.70
     fixme
    0.65
    (),
    0.62
    /"
    0.60
    isSpecialOrderable
    0.60
    edi
    0.60
    ();
    0.60
     whereas
    0.59
    ](
    0.58
     Grassley
    0.58
    Act Density 0.408%

    No Known Activations