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

    Neuronpedia

    INDEX
    Explanations

    statements about the current state or condition of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    füg
    -0.16
    amy
    -0.15
    uito
    -0.13
    stm
    -0.13
     happens
    -0.13
     added
    -0.13
    ubu
    -0.13
    enga
    -0.13
    ead
    -0.13
    vana
    -0.13
    POSITIVE LOGITS
     similar
    0.24
    缸åIJĮ
    0.22
     simple
    0.21
     identical
    0.21
     unchanged
    0.20
     theirs
    0.20
    ä¸Ģæł·
    0.20
     ones
    0.19
    similar
    0.18
     changed
    0.18
    Act Density 0.277%

    No Known Activations