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

    Neuronpedia

    INDEX
    Explanations

    assertions about the connection between actions and motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unda
    -0.15
     fully
    -0.15
     completely
    -0.15
    irl
    -0.15
     refresh
    -0.14
    rip
    -0.14
    羣æŃ£
    -0.14
     true
    -0.14
     aside
    -0.14
     stalk
    -0.14
    POSITIVE LOGITS
     convenient
    0.25
     Convenient
    0.23
     convenience
    0.20
     Convenience
    0.19
     conveniently
    0.18
    appe
    0.17
     Appe
    0.16
     Ñĥдоб
    0.16
    ickle
    0.16
     popularity
    0.15
    Act Density 0.497%

    No Known Activations