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

    Neuronpedia

    INDEX
    Explanations

    common pronouns and words that indicate relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hyp
    -0.17
     hypoth
    -0.15
     excess
    -0.14
    som
    -0.14
    ties
    -0.14
    rais
    -0.13
     kul
    -0.13
     eye
    -0.13
    emp
    -0.13
     Sand
    -0.13
    POSITIVE LOGITS
    ertime
    0.16
    horn
    0.15
    -chevron
    0.15
     Nest
    0.15
    alama
    0.14
     zach
    0.14
    Sharper
    0.14
    umat
    0.14
    åł´
    0.14
    ÑĸÑĪ
    0.14
    Act Density 0.004%

    No Known Activations