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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iens
    -0.15
    å¤ĩ
    -0.15
    ajs
    -0.15
    اجع
    -0.14
     ActionTypes
    -0.13
    ersistence
    -0.13
    ÏĨÏĮ
    -0.13
    ayload
    -0.13
    باÙĨ
    -0.13
    ردÙĩ
    -0.13
    POSITIVE LOGITS
     anything
    0.22
     nothing
    0.22
     anyone
    0.19
     Nothing
    0.17
    linger
    0.17
     anybody
    0.17
    nothing
    0.17
     NOTHING
    0.16
     Anyone
    0.16
    anything
    0.16
    Act Density 0.065%

    No Known Activations