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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating close association or partnership between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the idea of conjunction or pairing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.67
    é¾
    -0.65
    Registration
    -0.62
    ILE
    -0.60
     Nightmares
    -0.59
    IUM
    -0.58
    ãĤ¤ãĥĪ
    -0.57
    Stage
    -0.57
    urous
    -0.56
    ISON
    -0.55
    POSITIVE LOGITS
     glove
    1.02
    eger
    0.86
    monds
    0.79
    ither
    0.75
     toe
    0.71
    grand
    0.71
     cheek
    0.69
     heels
    0.68
    auga
    0.67
     heel
    0.67
    Act Density 0.062%

    No Known Activations