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

    Neuronpedia

    INDEX
    Explanations

    phrases related to liability and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ith
    -0.16
    olum
    -0.14
    ita
    -0.14
    rets
    -0.14
     æ¥
    -0.14
    åĥį
    -0.14
     xem
    -0.13
    ix
    -0.13
    icros
    -0.13
    ices
    -0.13
    POSITIVE LOGITS
     Gregg
    0.15
     Charm
    0.14
    RuntimeObject
    0.14
    ooter
    0.14
    mans
    0.14
    Å¡t
    0.14
     booty
    0.14
    trie
    0.14
    tober
    0.13
    bow
    0.13
    Act Density 0.026%

    No Known Activations