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

    Neuronpedia

    INDEX
    Explanations

    words related to density or thickness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thick" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ination
    -0.66
     starring
    -0.66
    FAULT
    -0.66
    perty
    -0.65
     Million
    -0.64
     GEAR
    -0.63
     externalToEVAOnly
    -0.63
    orers
    -0.62
    ARCH
    -0.61
    inatory
    -0.61
    POSITIVE LOGITS
    ened
    1.46
    ening
    1.43
    nesses
    1.33
    ness
    1.15
    ener
    1.12
    ly
    1.04
    ens
    1.01
    entimes
    0.99
    layer
    0.98
    est
    0.93
    Act Density 0.017%

    No Known Activations