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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing potential outcomes and future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    즈
    -0.46
     Boy
    -0.42
    assert
    -0.41
    WEBPACK
    -0.41
    <bos>
    -0.39
     bezig
    -0.39
    yní
    -0.39
    Begin
    -0.38
     års
    -0.38
     (
    -0.38
    POSITIVE LOGITS
    IntoConstraints
    0.96
     succeed
    0.94
    uxxxx
    0.91
     betweenstory
    0.89
     succeeds
    0.88
    DockStyle
    0.88
     someday
    0.78
     acquittal
    0.75
    IndentedString
    0.75
     eventually
    0.74
    Act Density 0.258%

    No Known Activations