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

    Neuronpedia

    INDEX
    Explanations

    instances of significant events or situations involving oversight and systemic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Strings
    -0.15
     Intermediate
    -0.15
    ogh
    -0.14
     kone
    -0.14
    най
    -0.13
    oti
    -0.13
    .Void
    -0.13
    aaS
    -0.13
    Intermediate
    -0.13
     intermediate
    -0.13
    POSITIVE LOGITS
     later
    0.66
    later
    0.52
    Later
    0.50
     Later
    0.49
     soon
    0.47
     shortly
    0.46
     months
    0.42
     weeks
    0.42
     später
    0.39
     years
    0.38
    Act Density 0.426%

    No Known Activations