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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating purpose or reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poÄįet
    -0.15
    ivol
    -0.15
    дем
    -0.14
    ienne
    -0.14
    inan
    -0.14
    rug
    -0.14
    rats
    -0.14
    åĻ
    -0.14
    arget
    -0.14
    æĢİ
    -0.14
    POSITIVE LOGITS
    ìį¨
    0.24
    -called
    0.21
     forth
    0.20
     that
    0.18
    inel
    0.17
    zial
    0.17
     future
    0.16
    oth
    0.16
     proper
    0.15
    elman
    0.15
    Act Density 0.048%

    No Known Activations