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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to substantiation or lack thereof in arguments or claims

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substantiation or evidence in claims or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blues
    -0.76
     Blues
    -0.74
     handlers
    -0.73
     Wilderness
    -0.66
     bloom
    -0.65
     tickets
    -0.65
     wings
    -0.63
     download
    -0.63
     players
    -0.62
     Blue
    -0.61
    POSITIVE LOGITS
    stant
    4.51
    stantial
    1.88
     Constantin
    1.24
    nces
    1.14
     Constant
    1.12
    stellar
    1.09
    rad
    1.08
    tle
    1.05
    etheless
    1.04
    oslav
    1.04
    Act Density 0.021%

    No Known Activations