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

    Neuronpedia

    INDEX
    Explanations

    keywords related to molecules and molecular structures

    oai_token-act-pair · gpt-3.5-turbo

    references to molecules and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.83
    į
    -0.83
    shire
    -0.81
    ership
    -0.79
    Disney
    -0.78
    ²
    -0.77
    san
    -0.77
     Freddy
    -0.74
    ij士
    -0.73
    RM
    -0.72
    POSITIVE LOGITS
    cules
    1.39
     molecules
    1.28
     molecule
    1.23
     nitrogen
    1.06
    cule
    0.94
     oxygen
    0.92
     oxide
    0.89
     chemically
    0.85
     atoms
    0.85
     chemistry
    0.85
    Act Density 0.014%

    No Known Activations