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

    Neuronpedia

    INDEX
    Explanations

    terms connected with causality or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causality or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tough
    -0.64
     average
    -0.63
     basics
    -0.63
     Dynasty
    -0.60
     dozen
    -0.60
     Summer
    -0.59
     rough
    -0.59
    ize
    -0.57
     big
    -0.57
     tech
    -0.56
    POSITIVE LOGITS
     thereby
    3.44
     thus
    1.69
     thence
    1.66
     hence
    1.56
     therein
    1.55
     consequently
    1.54
     therefore
    1.42
     hereby
    1.36
     furthermore
    1.36
     accordingly
    1.31
    Act Density 0.018%

    No Known Activations