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

    Neuronpedia

    INDEX
    Explanations

    words related to legal terms or lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events or milestones in a timeline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .).
    -0.55
    onto
    -0.54
    instead
    -0.51
    usercontent
    -0.51
     instead
    -0.51
     therein
    -0.50
    Compat
    -0.50
    ".[
    -0.50
    .�
    -0.48
    oshenko
    -0.48
    POSITIVE LOGITS
    haw
    0.53
     meanwhile
    0.52
    successful
    0.52
    design
    0.49
    moon
    0.48
    tails
    0.48
     Tribune
    0.48
     nutshell
    0.48
    eous
    0.47
    numbered
    0.46
    Act Density 1.447%

    No Known Activations