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

    Neuronpedia

    INDEX
    Explanations

    words related to negative events or situations that require some form of official intervention or action

    oai_token-act-pair · gpt-3.5-turbo

    situations that involve police intervention and related legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oros
    -0.62
    natureconservancy
    -0.59
    \",
    -0.59
    yss
    -0.56
    ï¸
    -0.56
    estern
    -0.56
     --------
    -0.54
     ----------------
    -0.54
     differs
    -0.54
    podcast
    -0.53
    POSITIVE LOGITS
     attest
    0.62
     prematurely
    0.58
     unwitting
    0.58
     denouncing
    0.55
     theirs
    0.54
    .).
    0.53
     panicked
    0.53
     nonexistent
    0.53
     nearby
    0.51
     bailout
    0.51
    Act Density 1.294%

    No Known Activations