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

    Neuronpedia

    INDEX
    Explanations

    social media or communication-related headings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character 'w/' in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agos
    -0.72
     obliged
    -0.65
     Reconstruction
    -0.65
    emort
    -0.63
    yrinth
    -0.62
     snipp
    -0.62
     Lumpur
    -0.60
    istar
    -0.59
    vertis
    -0.59
    terness
    -0.59
    POSITIVE LOGITS
    sole
    0.68
    stood
    0.66
    hold
    0.64
    AFP
    0.64
    lain
    0.64
    lde
    0.63
    Mot
    0.63
    ÏĢ
    0.62
    ste
    0.61
    ATIONS
    0.61
    Act Density 0.025%

    No Known Activations