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

    Neuronpedia

    INDEX
    Explanations

    words related to traveling by hopping or jumping

    oai_token-act-pair · gpt-3.5-turbo

    references to hops in the context of brewing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     payable
    -0.81
     reconc
    -0.62
     Printed
    -0.61
     withd
    -0.61
     conclud
    -0.60
     Aura
    -0.59
    Downloadha
    -0.57
     unfocusedRange
    -0.57
    ude
    -0.57
    ateral
    -0.57
    POSITIVE LOGITS
    eful
    1.13
    Hop
    1.07
    lite
    0.92
    stairs
    0.88
    efully
    0.87
    uls
    0.85
    shots
    0.85
    sticks
    0.84
     Hop
    0.84
    grass
    0.82
    Act Density 0.017%

    No Known Activations