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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to analysis and evaluation of conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    partements
    -0.56
    enment
    -0.52
    PostInfinity
    -0.51
     réfrig
    -0.47
    المناصب
    -0.47
    majánló
    -0.47
    delwed
    -0.46
    gangssprach
    -0.46
    oredCriteria
    -0.46
    səhifə
    -0.45
    POSITIVE LOGITS
     bc
    0.35
    EndContext
    0.34
    毕竟
    0.34
     getRule
    0.33
     externi
    0.32
    さすが
    0.32
     gau
    0.31
     StatelessWidget
    0.31
    AspNetCore
    0.31
     because
    0.31
    Act Density 0.469%

    No Known Activations