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

    Neuronpedia

    INDEX
    Explanations

    phrases related to travel and exploration

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with travel and exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibrary
    -0.78
    umn
    -0.72
    uga
    -0.68
    arel
    -0.66
    mx
    -0.66
    owl
    -0.65
    bidden
    -0.65
    ince
    -0.63
    ÃŃn
    -0.63
    ode
    -0.63
    POSITIVE LOGITS
     accordingly
    1.25
     alike
    0.91
     thereafter
    0.90
     thereof
    0.78
     resultant
    0.77
     afterward
    0.76
     afterwards
    0.75
     consequ
    0.74
     whichever
    0.70
     respectively
    0.68
    Act Density 0.753%

    No Known Activations