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

    Neuronpedia

    INDEX
    Explanations

    mentions of people's names in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    colons indicating lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.84
     turbulence
    -0.76
     behav
    -0.75
     behavi
    -0.72
     pursu
    -0.72
    undai
    -0.69
    ilater
    -0.67
     troubles
    -0.65
     overl
    -0.64
     padd
    -0.64
    POSITIVE LOGITS
     Yeah
    0.90
     Who
    0.84
     Rise
    0.82
     Bringing
    0.82
     Cosponsors
    0.81
     Reloaded
    0.79
    YES
    0.79
     Join
    0.78
     Provided
    0.77
     Originally
    0.76
    Act Density 0.086%

    No Known Activations