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

    Neuronpedia

    INDEX
    Explanations

    prepositions and locative expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    or
    -0.84
    er
    -0.83
    ity
    -0.74
    ir
    -0.73
    en
    -0.72
    ly
    -0.68
    ie
    -0.67
    in
    -0.66
    al
    -0.64
    um
    -0.62
    POSITIVE LOGITS
    CONSIN
    0.94
    omeness
    0.94
     в
    0.89
     يتيمه
    0.88
    rowave
    0.87
     В
    0.87
    éens
    0.83
     FormsModule
    0.83
    cessed
    0.83
    IBarButtonItem
    0.82
    Act Density 0.013%

    No Known Activations