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

    Neuronpedia

    INDEX
    Explanations

    dates of events

    oai_token-act-pair · gpt-3.5-turbo

    dates and their associated significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hobbies
    -0.64
    igham
    -0.61
     departments
    -0.60
    orable
    -0.59
     loves
    -0.58
     longstanding
    -0.56
     persecuted
    -0.56
     dwell
    -0.56
    icable
    -0.55
    GGGGGGGG
    -0.55
    POSITIVE LOGITS
    th
    1.34
    rd
    0.95
    ths
    0.91
    TH
    0.83
    teenth
    0.82
    eteenth
    0.73
    thus
    0.69
    ember
    0.68
    nd
    0.68
    ools
    0.67
    Act Density 0.086%

    No Known Activations