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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their frequency in relation to other words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.79
    。
    -0.56
    ".
    -0.54
    ;
    -0.52
    ).
    -0.51
    %.
    -0.49
    …
    -0.47
    ].
    -0.47
    ,
    -0.46
     Normdatei
    -0.46
    POSITIVE LOGITS
     كومونز
    0.79
    Portale
    0.77
     剪影
    0.77
    ='';
    0.76
     Audiodateien
    0.75
    TagHelpers
    0.75
     δὲ
    0.74
    $")
    0.74
     betweenstory
    0.72
     kaarangay
    0.72
    Act Density 0.666%

    No Known Activations