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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.66
     jsPsych
    -0.57
     CascadeType
    -0.56
    UnusedPrivate
    -0.56
    AsUp
    -0.54
    __*/
    -0.54
     AssemblyCulture
    -0.51
    脚注の使い方
    -0.51
    atività
    -0.50
     survi
    -0.49
    POSITIVE LOGITS
    owohl
    1.02
     tanto
    0.89
    Tanto
    0.83
    первых
    0.83
    neither
    0.76
     Tanto
    0.75
    ędzy
    0.74
    yarnpkg
    0.73
    enumi
    0.73
     neither
    0.71
    Act Density 0.291%

    No Known Activations