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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ER
    -0.53
     terce
    -0.51
    er
    -0.46
    лян
    -0.46
    引き続き
    -0.44
    PROBE
    -0.44
    Enumeration
    -0.44
    hasErrors
    -0.43
     Salter
    -0.43
    ത്ര
    -0.42
    POSITIVE LOGITS
     who
    1.13
    who
    0.95
    คนที่
    0.89
    Who
    0.79
     Who
    0.78
     chiunque
    0.77
    ISupport
    0.75
     that
    0.75
    ViewFeatures
    0.74
    whom
    0.74
    Act Density 0.265%

    No Known Activations