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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.55
    цездатний
    -0.54
    AndEndTag
    -0.54
    uxxxx
    -0.54
    DIRS
    -0.50
    -0.49
     Infórmanos
    -0.49
    }{||
    -0.48
    帖最后由
    -0.48
     ComVisible
    -0.46
    POSITIVE LOGITS
     πως
    0.69
     kerap
    0.58
     dunque
    0.57
     словно
    0.57
    retudo
    0.57
     wciąż
    0.56
    如今
    0.54
     désormais
    0.54
     chẳng
    0.53
     freilich
    0.53
    Act Density 0.017%

    No Known Activations