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

    Neuronpedia

    INDEX
    Explanations

    references to individual characteristics or aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amnesty
    -0.72
    Fon
    -0.60
    Bains
    -0.59
    wps
    -0.59
    Vern
    -0.58
     bailout
    -0.57
    ámara
    -0.57
     scare
    -0.56
     Koning
    -0.55
    cleros
    -0.55
    POSITIVE LOGITS
    ividual
    1.57
     individual
    1.39
     INDIVIDUAL
    1.38
     Individual
    1.38
    Individual
    1.29
    Individuals
    1.26
    IVIDUAL
    1.26
     individuals
    1.25
     Individuals
    1.23
    individual
    1.22
    Act Density 0.045%

    No Known Activations