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

    Neuronpedia

    INDEX
    Explanations

    formal communication cues and requests for information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therefore
    -0.21
     Therefore
    -0.18
    Therefore
    -0.18
     hence
    -0.17
     consequently
    -0.17
    ÑĢеп
    -0.16
     wiÄĻc
    -0.16
    aka
    -0.15
     thus
    -0.15
     Consequently
    -0.15
    POSITIVE LOGITS
    Alternatively
    0.32
     Alternatively
    0.29
     alternatively
    0.21
     Altern
    0.21
     Otherwise
    0.20
     otherwise
    0.20
     æĪĸ
    0.20
    Otherwise
    0.20
     Or
    0.19
     remember
    0.19
    Act Density 0.078%

    No Known Activations