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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "until"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "until"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hazard
    -0.75
    aque
    -0.71
    cap
    -0.69
    hack
    -0.68
    aird
    -0.68
    Friend
    -0.68
    eny
    -0.66
    Adds
    -0.66
    Expl
    -0.66
    Nic
    -0.65
    POSITIVE LOGITS
    soever
    0.85
    until
    0.76
    MENTS
    0.76
     msec
    0.75
    terday
    0.74
    swer
    0.70
     afterward
    0.70
     til
    0.69
     halfway
    0.69
    opa
    0.69
    Act Density 0.028%

    No Known Activations