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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve raising awareness or increasing visibility on various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cov
    -0.16
    iglia
    -0.16
    eters
    -0.15
    odor
    -0.15
    IENTATION
    -0.14
    iry
    -0.14
    lem
    -0.14
    zza
    -0.13
    igue
    -0.13
    çĬ¶æħĭ
    -0.13
    POSITIVE LOGITS
    _UNIX
    0.17
    eus
    0.16
    HM
    0.15
    uard
    0.15
    .gs
    0.15
     eyebrows
    0.15
    velt
    0.14
    tone
    0.14
    yla
    0.14
    gars
    0.14
    Act Density 0.031%

    No Known Activations