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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating physical or metaphorical movement or action

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating spatial or contextual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.72
    opt
    -0.63
    ource
    -0.62
    chell
    -0.60
    arent
    -0.59
    ickr
    -0.58
    amous
    -0.57
    hops
    -0.56
    wings
    -0.54
    cient
    -0.54
    POSITIVE LOGITS
     oneself
    0.74
     behalf
    0.67
     juven
    0.66
     humankind
    0.64
     undermin
    0.60
     mankind
    0.60
    Īè
    0.58
     Camel
    0.57
     subdu
    0.57
     submar
    0.57
    Act Density 0.831%

    No Known Activations