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

    Neuronpedia

    INDEX
    Explanations

    connections between words indicating history, classifications, or evaluations of concepts and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     experience
    -0.19
    aba
    -0.16
    experience
    -0.16
    331
    -0.16
    amam
    -0.15
    zej
    -0.15
     scenario
    -0.15
     Factors
    -0.15
     factors
    -0.15
    ppard
    -0.15
    POSITIVE LOGITS
     meaning
    0.24
     significance
    0.24
     relevance
    0.23
    Impact
    0.22
     impact
    0.21
    impact
    0.21
    Purpose
    0.21
     purpose
    0.20
    purpose
    0.20
     implications
    0.20
    Act Density 0.245%

    No Known Activations