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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.81
     scp
    -0.74
     Mao
    -0.72
     houſe
    -0.72
     Majefty
    -0.72
     onOptions
    -0.71
     Houſe
    -0.70
     purpoſe
    -0.69
     AMC
    -0.68
     Sae
    -0.67
    POSITIVE LOGITS
     With
    1.36
     WITH
    1.30
    With
    1.15
    WITH
    1.13
     Avec
    1.08
    with
    1.07
     with
    1.03
    Avec
    0.98
     the
    0.97
     Witherspoon
    0.95
    Act Density 0.399%

    No Known Activations