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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making significant changes or transitions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to initiating change or starting anew

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pecul
    -0.65
     Cosponsors
    -0.62
     interrupts
    -0.62
     Ramadan
    -0.60
    paralle
    -0.60
     overhe
    -0.60
    ibrary
    -0.59
     scanner
    -0.59
    dayName
    -0.59
    />
    -0.58
    POSITIVE LOGITS
     instead
    1.13
    instead
    1.10
    Instead
    0.99
     replaced
    0.95
     Instead
    0.83
     anew
    0.81
     substituted
    0.74
     revert
    0.72
     rebuilt
    0.70
    ynthesis
    0.70
    Act Density 0.540%

    No Known Activations