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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a connection or relationship with something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.69
    orthy
    -0.63
    hyde
    -0.63
    insula
    -0.63
    pai
    -0.62
     Shutterstock
    -0.62
    mallow
    -0.62
    iste
    -0.57
    rift
    -0.57
    igate
    -0.56
    POSITIVE LOGITS
     consequ
    0.95
     subsequent
    0.85
     ensuing
    0.83
     thereof
    0.79
     occasional
    0.77
    stood
    0.76
     good
    0.76
     accordingly
    0.76
     thereto
    0.75
    pired
    0.74
    Act Density 0.177%

    No Known Activations