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

    Neuronpedia

    INDEX
    Explanations

    phrases related to division or separation

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations or terms related to negative actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Confederation
    -0.69
     Chambers
    -0.67
     HH
    -0.64
     opposition
    -0.63
     KN
    -0.63
     existence
    -0.62
    izon
    -0.61
     Nicarag
    -0.59
     curved
    -0.59
     arrival
    -0.58
    POSITIVE LOGITS
    your
    1.15
    through
    1.09
    ups
    1.06
    up
    1.05
    rate
    1.02
    outs
    1.02
    around
    1.01
    out
    1.00
    fest
    0.99
    engine
    0.98
    Act Density 0.130%

    No Known Activations