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

    Neuronpedia

    INDEX
    Explanations

    expressions related to anticipation and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alic
    -0.15
    unned
    -0.15
    woord
    -0.14
    à¸Ħว
    -0.14
    credited
    -0.14
    erie
    -0.14
    ober
    -0.14
    hic
    -0.14
    inded
    -0.13
     Blowjob
    -0.13
    POSITIVE LOGITS
     promises
    0.23
     potentially
    0.22
     promising
    0.21
     interesting
    0.18
    pot
    0.17
     promise
    0.17
     fun
    0.17
     Fun
    0.16
    yang
    0.15
    kus
    0.15
    Act Density 0.129%

    No Known Activations