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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predominant
    -0.16
     overarching
    -0.14
    ivo
    -0.14
    PEnd
    -0.13
    fox
    -0.13
    scient
    -0.13
     covariance
    -0.13
     pronto
    -0.13
    eno
    -0.13
    eldo
    -0.12
    POSITIVE LOGITS
    ories
    0.21
     nature
    0.20
     question
    0.19
     term
    0.18
     mere
    0.18
     ability
    0.18
     literature
    0.18
     need
    0.18
     presence
    0.18
     sheer
    0.17
    Act Density 0.238%

    No Known Activations