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

    Neuronpedia

    INDEX
    Explanations

    phrases related to observations or opinions about various subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to see" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.77
    taboola
    -0.67
    nesia
    -0.65
    ÃŃa
    -0.65
    orem
    -0.64
     translator
    -0.64
    ium
    -0.63
    ella
    -0.63
     prophes
    -0.62
     hardest
    -0.61
    POSITIVE LOGITS
    enance
    0.78
     parallels
    0.76
     someone
    0.69
    ablishment
    0.69
     him
    0.68
     PSU
    0.68
     how
    0.68
     similarities
    0.65
     such
    0.63
     somebody
    0.62
    Act Density 0.044%

    No Known Activations