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

    Neuronpedia

    INDEX
    Explanations

    comparisons between multiple entities

    oai_token-act-pair · gpt-3.5-turbo

    comparisons and contrasts between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calendars
    -0.71
    hower
    -0.69
    soon
    -0.67
    otiation
    -0.66
     evac
    -0.66
    ults
    -0.66
     mobilized
    -0.65
    ezvous
    -0.64
     mobilize
    -0.63
     evacuation
    -0.63
    POSITIVE LOGITS
     flaws
    1.26
     uniqueness
    1.21
     shortcomings
    1.19
     pecul
    1.14
     distinguishing
    1.13
     drawbacks
    1.12
     similarities
    1.12
     resemb
    1.10
     weaknesses
    1.07
     quirks
    1.07
    Act Density 0.450%

    No Known Activations