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

    Neuronpedia

    INDEX
    Explanations

    phrases that relate to subjects and subjectivities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushing
    -0.17
    ersions
    -0.17
    ardo
    -0.16
    usp
    -0.16
    ocker
    -0.15
    uder
    -0.15
    sters
    -0.15
     Sabha
    -0.15
    isters
    -0.15
    undry
    -0.15
    POSITIVE LOGITS
    ivity
    0.43
    ively
    0.42
     matter
    0.41
    matter
    0.36
    ivities
    0.35
     Matter
    0.31
    ivism
    0.30
    ive
    0.29
    ivist
    0.28
    IVE
    0.24
    Act Density 0.016%

    No Known Activations