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

    Neuronpedia

    INDEX
    Explanations

    events, actions, or concepts related to high-stakes situations

    oai_token-act-pair · gpt-3.5-turbo

    contexts involving high technology or high-stakes situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     halves
    -0.79
     Dull
    -0.75
     Creator
    -0.73
     Maher
    -0.71
     XD
    -0.71
     Bj
    -0.69
     Friends
    -0.68
     Shell
    -0.68
     classics
    -0.68
     wedd
    -0.67
    POSITIVE LOGITS
    profile
    1.65
    intensity
    1.57
    tech
    1.57
    speed
    1.57
    stakes
    1.56
    ranking
    1.56
    definition
    1.55
    pressure
    1.55
    risk
    1.55
    quality
    1.53
    Act Density 0.030%

    No Known Activations