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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific terms related to various topics such as policy, organizations, events, and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizational entities, projects, and community initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reliably
    -0.64
    VERTISEMENT
    -0.62
     ));
    -0.61
     fertile
    -0.60
     predictable
    -0.60
     glance
    -0.58
     measured
    -0.58
     decl
    -0.58
     step
    -0.57
     wedge
    -0.56
    POSITIVE LOGITS
    estine
    0.90
    foundland
    0.87
    tainment
    0.85
    anmar
    0.84
    anamo
    0.83
    odore
    0.82
    etheus
    0.82
    anyahu
    0.80
    Chem
    0.80
    ablishment
    0.78
    Act Density 0.264%

    No Known Activations