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

    Neuronpedia

    INDEX
    Explanations

    instances of quantity or inclusivity in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pu
    -0.18
    jde
    -0.17
    elor
    -0.15
    onium
    -0.15
    ertia
    -0.15
    enthal
    -0.15
    å°¾
    -0.14
    uffers
    -0.14
    ewhere
    -0.14
    PU
    -0.13
    POSITIVE LOGITS
     jun
    0.31
     times
    0.30
     points
    0.22
     Jun
    0.22
     given
    0.21
     GIVEN
    0.19
    times
    0.19
    Jun
    0.19
    _times
    0.18
     stages
    0.18
    Act Density 0.030%

    No Known Activations