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

    Neuronpedia

    INDEX
    Explanations

    contractions followed by actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    future tense verbs indicating plans or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cule
    -0.71
    ional
    -0.71
    CTV
    -0.68
    uria
    -0.65
    ModLoader
    -0.64
    Reviewer
    -0.63
    soever
    -0.63
    Reloaded
    -0.62
     signifies
    -0.61
    amped
    -0.57
    POSITIVE LOGITS
     gladly
    0.98
     probably
    0.94
     be
    0.90
     admit
    0.89
     never
    0.83
     gotta
    0.82
     stick
    0.81
     doubtless
    0.80
     forgive
    0.78
     miss
    0.77
    Act Density 0.053%

    No Known Activations