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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce uncertainty or conditional situations

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

    "Whether" followed by a clause

    np_acts-logits-general · gemini-2.0-flash

    Whether or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -1.07
    AndEndTag
    -0.96
    ſelf
    -0.92
     purpoſe
    -0.91
     Jefus
    -0.90
     pleaſure
    -0.89
     Monfieur
    -0.89
     houſe
    -0.89
     الحره
    -0.88
     raiſ
    -0.88
    POSITIVE LOGITS
     they
    0.96
     WHETHER
    0.92
     there
    0.88
     it
    0.85
     whether
    0.84
     we
    0.82
    whether
    0.82
     Whether
    0.79
    Whether
    0.79
     you
    0.77
    Act Density 0.049%

    No Known Activations