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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a conclusion, judgment, or explanation

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.83
    aukee
    -0.80
    izont
    -0.71
    Lex
    -0.70
    PRESS
    -0.70
    vre
    -0.64
    IUM
    -0.63
    MX
    -0.61
    Luck
    -0.61
    Robin
    -0.60
    POSITIVE LOGITS
     consequently
    0.95
     culminated
    0.78
     they
    0.78
     furthermore
    0.74
    soever
    0.74
     reconc
    0.73
    cher
    0.70
     therefore
    0.69
     although
    0.68
     resulted
    0.68
    Act Density 0.107%

    No Known Activations