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

    Neuronpedia

    INDEX
    Explanations

    references to assistance or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favourably
    -0.46
    >`;
    -0.46
     favorably
    -0.46
    SerializedSize
    -0.43
    )');
    -0.43
     helping
    -0.42
     stems
    -0.41
     "..\..\..\
    -0.40
    )"),
    -0.39
    helping
    -0.39
    POSITIVE LOGITS
     aid
    0.61
    ThroughAttribute
    0.59
    coltà
    0.54
     invite
    0.53
    exitRule
    0.53
     faculty
    0.52
     invitation
    0.51
     Aid
    0.50
     snippetHide
    0.50
     thesis
    0.50
    Act Density 0.200%

    No Known Activations