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

    Neuronpedia

    INDEX
    Explanations

    the word "no" regardless of the context

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing negation or the concept of "no."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iership
    -0.74
    RAFT
    -0.72
    ktop
    -0.71
    endar
    -0.69
    assies
    -0.66
    hip
    -0.64
    lycer
    -0.63
    rex
    -0.63
    ropolitan
    -0.62
    geist
    -0.61
    POSITIVE LOGITS
    xious
    1.29
     matter
    1.07
     longer
    1.03
    except
    0.95
     doubt
    0.93
    etheless
    0.92
    vell
    0.87
    oses
    0.85
    ct
    0.83
    oooooooo
    0.83
    Act Density 0.107%

    No Known Activations