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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the special character âĢĶ and its variations, suggesting a focus on specific formatting or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Kay
    -0.67
    nai
    -0.63
    urable
    -0.63
    ulated
    -0.60
    ains
    -0.60
    ulp
    -0.59
    LV
    -0.58
    iph
    -0.58
     Wake
    -0.56
    IFF
    -0.55
    POSITIVE LOGITS
     convol
    0.82
     chances
    0.81
    then
    0.75
    terday
    0.72
    osate
    0.69
    anwhile
    0.67
    ]).
    0.67
    ]),
    0.66
     nevertheless
    0.66
    chwitz
    0.65
    Act Density 0.757%

    No Known Activations