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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "previously" or time-related references

    oai_token-act-pair · gpt-3.5-turbo

    references to time and temporal transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aby
    -0.71
    wake
    -0.69
    atur
    -0.68
    =>
    -0.67
    rench
    -0.67
    redo
    -0.66
    akens
    -0.65
    Rush
    -0.65
    Notice
    -0.65
    Rust
    -0.65
    POSITIVE LOGITS
     consisted
    0.78
     hadn
    0.77
     existed
    0.69
     relied
    0.68
    had
    0.67
     weren
    0.66
     wasn
    0.64
    didn
    0.64
     didn
    0.64
     tended
    0.64
    Act Density 0.291%

    No Known Activations