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

    Neuronpedia

    INDEX
    Explanations

    terms related to apologies and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to apologies and cash transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ument
    -0.73
    ality
    -0.66
    hof
    -0.63
    thal
    -0.63
    ¢
    -0.63
    Downloadha
    -0.61
     Arabian
    -0.61
     Lights
    -0.60
    braska
    -0.59
    acht
    -0.59
    POSITIVE LOGITS
    etics
    0.98
    andra
    0.92
    orial
    0.91
    gow
    0.91
    iar
    0.91
    eteria
    0.85
    etic
    0.84
    mers
    0.81
    hers
    0.81
    esome
    0.78
    Act Density 0.060%

    No Known Activations