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

    Neuronpedia

    INDEX
    Explanations

    words related to specific actions or activities, particularly involving individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    the Spanish conjunction "and" (y) and instances where it appears in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.83
    spring
    -0.77
    itates
    -0.74
    wagen
    -0.72
    sis
    -0.72
    spin
    -0.70
    space
    -0.69
    itatively
    -0.69
    itate
    -0.67
    rooms
    -0.66
    POSITIVE LOGITS
    ando
    0.90
    agate
    0.87
    elta
    0.78
    ragon
    0.76
    onga
    0.76
    jo
    0.75
    ploy
    0.75
     Alonso
    0.74
    ques
    0.73
    ño
    0.71
    Act Density 0.030%

    No Known Activations