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

    Neuronpedia

    INDEX
    Explanations

    words related to hiding or concealing

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or states of being, particularly those associated with responsibility or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.70
    omez
    -0.63
    aughtered
    -0.61
    enhagen
    -0.60
    dl
    -0.59
    ources
    -0.58
    ensen
    -0.58
    ahime
    -0.58
    umbn
    -0.57
    thia
    -0.56
    POSITIVE LOGITS
    pillar
    0.75
    lehem
    0.74
    levard
    0.72
    halla
    0.68
    ĪĴ
    0.67
    apest
    0.67
    artisan
    0.64
     Commando
    0.64
    abase
    0.64
     Haram
    0.64
    Act Density 0.106%

    No Known Activations