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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases often used in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.20
    $MESS
    -0.16
    /INFO
    -0.16
    deaux
    -0.15
    $LANG
    -0.14
    corr
    -0.14
    isz
    -0.14
    δικ
    -0.14
    alom
    -0.14
    .wordpress
    -0.13
    POSITIVE LOGITS
    gether
    0.34
    atre
    0.26
    ftware
    0.20
    apons
    0.20
    ir
    0.19
    clusive
    0.19
    oret
    0.18
    zelf
    0.18
    oner
    0.18
    ater
    0.18
    Act Density 0.064%

    No Known Activations