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

    Neuronpedia

    INDEX
    Explanations

    phrases related to propositions or premises

    oai_token-act-pair · gpt-3.5-turbo

    terms related to propositions and premises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocker
    -0.80
    ularity
    -0.76
    pine
    -0.76
    lake
    -0.74
    thumbnails
    -0.73
    owing
    -0.73
    itsch
    -0.72
    fax
    -0.71
    irtual
    -0.71
    upt
    -0.70
    POSITIVE LOGITS
     proposition
    0.92
    ually
    0.84
     premise
    0.82
    aur
    0.67
     hypothes
    0.67
     false
    0.66
    itious
    0.66
    -+-+
    0.66
     propositions
    0.65
     untrue
    0.64
    Act Density 0.076%

    No Known Activations