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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental results and accuracy in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortex
    -0.16
    .Usage
    -0.15
    Decorator
    -0.15
    ectors
    -0.14
    irates
    -0.13
    lys
    -0.13
    dpi
    -0.13
    arel
    -0.13
    xbf
    -0.13
    pons
    -0.13
    POSITIVE LOGITS
     ent
    0.30
     heats
    0.27
    enthal
    0.27
     Gibbs
    0.23
    _ent
    0.22
     entropy
    0.22
     therm
    0.22
     Antoine
    0.21
     expans
    0.21
     heat
    0.21
    Act Density 0.014%

    No Known Activations