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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases indicating duration or time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arness
    -0.18
    ongan
    -0.18
    gross
    -0.16
     Shemale
    -0.15
    ÃŃrk
    -0.15
    _utilities
    -0.15
     brun
    -0.15
    ç¸
    -0.15
    layers
    -0.14
    ÑĢой
    -0.14
    POSITIVE LOGITS
     Proud
    0.16
    wc
    0.16
     wen
    0.15
    IGHLIGHT
    0.15
     cubes
    0.15
     pressure
    0.14
     shortly
    0.14
    ÏĦÏī
    0.14
     pert
    0.14
     Relax
    0.14
    Act Density 0.110%

    No Known Activations