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

    Neuronpedia

    INDEX
    Explanations

    trigger words indicating a change in topic or speaker

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shroud
    -0.85
     shrouded
    -0.69
     semblance
    -0.69
     grips
    -0.68
     leaps
    -0.68
     residence
    -0.68
     representation
    -0.67
     envelop
    -0.65
     transfer
    -0.64
     visitor
    -0.64
    POSITIVE LOGITS
    ł
    1.26
    ¹
    1.22
    ª
    1.15
    ONSORED
    1.08
    ij
    1.05
    IJ
    1.05
    Ĵ
    1.04
    ¦
    1.02
    ¡
    1.02
    £
    1.00
    Act Density 0.086%

    No Known Activations