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

    Neuronpedia

    INDEX
    Explanations

    actions related to observational experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uin
    -0.16
    ÑĢиÑĩ
    -0.15
    vero
    -0.15
    les
    -0.15
    cki
    -0.14
    ucer
    -0.14
    á»ĭch
    -0.14
     báºŃc
    -0.14
    cle
    -0.14
    metics
    -0.14
    POSITIVE LOGITS
     upon
    0.21
     down
    0.17
     around
    0.17
     ahead
    0.16
     alike
    0.16
     dag
    0.16
     sky
    0.16
     forward
    0.16
    _iff
    0.15
    Glass
    0.15
    Act Density 0.046%

    No Known Activations