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

    Neuronpedia

    INDEX
    Explanations

    the verb "is" followed by descriptions or statements

    oai_token-act-pair · gpt-3.5-turbo

    the word "is" indicating statements of existence or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.76
     Chero
    -0.70
     Isles
    -0.64
     Seym
    -0.63
    rouse
    -0.63
    isphere
    -0.61
     stones
    -0.60
    edIn
    -0.60
     coasts
    -0.60
    eteria
    -0.60
    POSITIVE LOGITS
    rael
    1.11
    senal
    0.85
    ometric
    0.83
     hereby
    0.82
    omorphic
    0.82
    olation
    0.80
    Offline
    0.77
    omorph
    0.76
     rated
    0.74
     deprecated
    0.74
    Act Density 0.049%

    No Known Activations