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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to the timing of events or the current status of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amin
    -0.70
    minecraft
    -0.70
     Scorp
    -0.69
     Lazarus
    -0.67
    cheat
    -0.67
     Auditor
    -0.67
    mens
    -0.65
    lez
    -0.64
    mat
    -0.64
    mare
    -0.63
    POSITIVE LOGITS
     unsuccessful
    0.63
     progressed
    0.63
    Ł
    0.63
     yielded
    0.62
     indications
    0.62
     elapsed
    0.62
     consisted
    0.61
     transpired
    0.61
     gone
    0.60
     unch
    0.60
    Act Density 0.054%

    No Known Activations