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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases emphasizing intent and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĻ
    -0.16
    amon
    -0.15
    anford
    -0.14
    ienne
    -0.14
    thritis
    -0.14
    .radioButton
    -0.14
    ivol
    -0.14
    poÄįet
    -0.14
     xong
    -0.14
     TIMEOUT
    -0.14
    POSITIVE LOGITS
    ìį¨
    0.19
     that
    0.18
    inel
    0.17
     forth
    0.17
     future
    0.17
    -called
    0.15
    774
    0.15
     afin
    0.15
    upa
    0.15
     hopefully
    0.15
    Act Density 0.046%

    No Known Activations