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

    Neuronpedia

    INDEX
    Explanations

    alternative options and conditional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -0.90
    addCriterion
    -0.88
     Majefty
    -0.87
    WebElementEntity
    -0.85
     ―――――
    -0.82
     ་་
    -0.77
     houſe
    -0.77
     myſelf
    -0.76
     étoient
    -0.76
     ſeveral
    -0.75
    POSITIVE LOGITS
     alternatively
    0.88
     Alternatively
    0.84
     else
    0.77
    Else
    0.70
    Alternatively
    0.69
     alternativ
    0.64
     Otherwise
    0.62
    Otherwise
    0.62
     OR
    0.61
     otherwise
    0.61
    Act Density 0.232%

    No Known Activations