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

    Neuronpedia

    INDEX
    Explanations

    phrases related to training camps

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the progression of events or timelines in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     discriminated
    -0.72
     unfairly
    -0.65
     exceptions
    -0.65
     harmed
    -0.65
     exception
    -0.65
     interfered
    -0.64
     indirectly
    -0.63
    edi
    -0.63
     influenced
    -0.61
     weak
    -0.61
    POSITIVE LOGITS
     countdown
    0.89
    dule
    0.76
     Celebration
    0.72
     FINAL
    0.72
     Deadline
    0.70
     Prepare
    0.69
     preparations
    0.68
     festivities
    0.68
    final
    0.67
    prep
    0.65
    Act Density 1.580%

    No Known Activations