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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating movement or direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate movement or attendance to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.60
    hler
    -0.59
    BSD
    -0.57
    imov
    -0.57
    NPR
    -0.55
     debuted
    -0.55
    iera
    -0.54
    Released
    -0.54
     retrieved
    -0.53
    iasco
    -0.53
    POSITIVE LOGITS
     oneself
    0.90
     anything
    0.71
    ordinate
    0.68
    ateral
    0.63
    rue
    0.62
     parity
    0.62
    anything
    0.61
     advantageous
    0.61
    your
    0.60
     certain
    0.60
    Act Density 0.684%

    No Known Activations