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

    Neuronpedia

    INDEX
    Explanations

    phrases describing distance or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to distances or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciplinary
    -0.62
     Naj
    -0.61
     informed
    -0.59
    PLIC
    -0.58
     Anonymous
    -0.58
    iku
    -0.58
    opic
    -0.57
    IU
    -0.57
     addressed
    -0.56
     NGO
    -0.56
    POSITIVE LOGITS
    sometimes
    0.67
    loads
    0.66
    usually
    0.66
     reliably
    0.66
    phies
    0.66
    maxwell
    0.64
    even
    0.64
     ALWAYS
    0.64
    depending
    0.63
    renheit
    0.62
    Act Density 0.722%

    No Known Activations