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

    Neuronpedia

    INDEX
    Explanations

    inclusive and complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Meanwhile
    -0.22
     Meanwhile
    -0.21
     eventually
    -0.19
     dabei
    -0.17
    Eventually
    -0.17
     ultimately
    -0.17
     meanwhile
    -0.16
    enet
    -0.16
     Afterwards
    -0.16
    apore
    -0.16
    POSITIVE LOGITS
     although
    0.30
     unlike
    0.26
     instead
    0.25
     Instead
    0.23
     despite
    0.23
     while
    0.22
    although
    0.22
     since
    0.21
     after
    0.21
     upon
    0.20
    Act Density 0.044%

    No Known Activations