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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or clauses that imply potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alara
    -0.16
    ردÙĩ
    -0.15
    pekt
    -0.15
    owski
    -0.14
    /sys
    -0.14
    lies
    -0.14
    .mybatisplus
    -0.14
     almost
    -0.13
    intage
    -0.13
     statewide
    -0.13
    POSITIVE LOGITS
     somehow
    0.22
     eventually
    0.18
     ultimately
    0.18
     indeed
    0.18
     nothing
    0.18
     successful
    0.17
     succeed
    0.17
     trends
    0.17
     hypoth
    0.16
    current
    0.16
    Act Density 0.105%

    No Known Activations