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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical or metaphorical pathways or journeys

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a journey or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.67
     reuse
    -0.63
    anton
    -0.63
    ervation
    -0.61
    onics
    -0.60
    imble
    -0.60
    ise
    -0.59
    igel
    -0.59
    »Ĵ
    -0.58
     Scene
    -0.58
    POSITIVE LOGITS
    nir
    0.81
    forward
    0.79
     down
    0.77
    points
    0.73
    forth
    0.69
    ward
    0.68
    around
    0.67
    round
    0.67
     through
    0.66
    fare
    0.65
    Act Density 0.029%

    No Known Activations