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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "till" which may indicate a limit, point in time, or condition

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related terms indicating continuation or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Phill
    -0.78
    REF
    -0.76
    insula
    -0.76
    Christ
    -0.73
    Charl
    -0.73
    Nich
    -0.72
    Scott
    -0.72
    Emily
    -0.71
    Mary
    -0.71
    Gaza
    -0.69
    POSITIVE LOGITS
     till
    0.83
    soever
    0.76
     Nadu
    0.75
    stals
    0.73
    ices
    0.72
    rack
    0.71
     thou
    0.69
     Krishna
    0.69
    ality
    0.68
    redo
    0.68
    Act Density 0.011%

    No Known Activations