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

    Neuronpedia

    INDEX
    Explanations

    events or situations

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases beginning with "Things" that indicate change or progression in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eus
    -0.78
    iary
    -0.69
    aye
    -0.68
    Joined
    -0.67
    asking
    -0.65
     theorem
    -0.65
    lication
    -0.62
    odied
    -0.61
    oard
    -0.61
    ELD
    -0.61
    POSITIVE LOGITS
     deteriorated
    1.01
     escalated
    1.01
     transpired
    0.98
     escalate
    0.96
     snowball
    0.91
     calmed
    0.89
     unravel
    0.89
     deterior
    0.89
     worsened
    0.86
     unfolded
    0.85
    Act Density 0.091%

    No Known Activations