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

    Neuronpedia

    INDEX
    Explanations

    details about events being canceled or closed

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating cancellation or closure due to various reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toget
    -0.76
    vir
    -0.76
    enos
    -0.76
    eh
    -0.73
    FIELD
    -0.70
    enne
    -0.69
    horn
    -0.67
    represented
    -0.67
    Narr
    -0.66
    minecraft
    -0.66
    POSITIVE LOGITS
     indefinitely
    0.82
     expired
    0.77
     due
    0.77
     redundancy
    0.74
     redundant
    0.71
     layoffs
    0.69
     involuntary
    0.69
    due
    0.68
     reopened
    0.68
     Daylight
    0.68
    Act Density 0.546%

    No Known Activations