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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing specific conditions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    the word "which" and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Behind
    -0.79
    athi
    -0.73
    Bas
    -0.68
    WARE
    -0.64
    Bo
    -0.62
    Gy
    -0.62
    grim
    -0.60
     Baker
    -0.60
    Brother
    -0.60
     Buc
    -0.59
    POSITIVE LOGITS
    soever
    0.92
    allows
    0.79
     resulted
    0.79
     incidentally
    0.78
     includes
    0.78
     consists
    0.78
     brings
    0.77
     contrasts
    0.76
     comprises
    0.74
     prompts
    0.74
    Act Density 0.138%

    No Known Activations