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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the performance or success of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    doing well or poorly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Effective
    -0.41
    ApiModelProperty
    -0.40
    Effective
    -0.37
    <%@
    -0.35
     effective
    -0.32
    னி
    -0.31
     걸
    -0.30
    uiente
    -0.30
     Orb
    -0.30
    SourceChecksum
    -0.30
    POSITIVE LOGITS
    better
    0.99
     fared
    0.97
     better
    0.95
     mieux
    0.92
     poorly
    0.87
     BETTER
    0.82
     worse
    0.81
    Better
    0.81
     fare
    0.79
     well
    0.79
    Act Density 0.054%

    No Known Activations