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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of a specific word or phrase related to identity and recurring themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faſt
    -0.54
     vixion
    -0.54
    HtmlAttribute
    -0.52
     feroit
    -0.51
     Eſ
    -0.50
     useStyles
    -0.48
     auroit
    -0.48
     avoient
    -0.46
     ſtre
    -0.45
    ScopeManager
    -0.45
    POSITIVE LOGITS
     duplicate
    0.69
     ass
    0.66
    mybatisplus
    0.63
     dup
    0.60
     Duplicate
    0.60
     satellite
    0.59
    inger
    0.59
    Duplicate
    0.58
     spare
    0.58
     ghost
    0.55
    Act Density 0.564%

    No Known Activations