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

    Neuronpedia

    INDEX
    Explanations

    comparisons being made between different scenarios or situations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "just as" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bryce
    -0.75
    meet
    -0.68
    hack
    -0.68
    aux
    -0.67
    oes
    -0.66
    only
    -0.66
    u
    -0.66
    alian
    -0.65
    Ve
    -0.64
     sleeper
    -0.63
    POSITIVE LOGITS
    lihood
    0.83
     advertised
    0.81
     stressed
    0.70
    atom
    0.70
     importantly
    0.69
     princ
    0.65
    ©¶æ
    0.64
    imilar
    0.62
    aths
    0.62
    ikh
    0.62
    Act Density 0.026%

    No Known Activations