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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to biochemical processes and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.71
    στή
    -0.55
    ductors
    -0.50
    halten
    -0.49
    }{||
    -0.48
    TagHelper
    -0.48
    Numerology
    -0.47
    DEFINITIONS
    -0.47
    PropertyGroup
    -0.46
     play
    -0.46
    POSITIVE LOGITS
     experiences
    0.85
     contracts
    0.66
     Experiences
    0.65
     acts
    0.63
     secret
    0.61
     rehe
    0.61
     cruises
    0.60
    experiences
    0.59
     forms
    0.59
     stores
    0.59
    Act Density 0.751%

    No Known Activations