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

    Neuronpedia

    INDEX
    Explanations

    words related to frequency or recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.98
    DockStyle
    -0.98
     يتيمه
    -0.96
     propOrder
    -0.90
    RetentionPolicy
    -0.87
    setVerticalGroup
    -0.86
    ⓧ
    -0.85
    Portály
    -0.84
    XmlAccessType
    -0.82
    IntoConstraints
    -0.80
    POSITIVE LOGITS
     being
    0.82
     is
    0.81
     becoming
    0.76
     becomes
    0.73
     be
    0.71
     être
    0.66
     are
    0.65
     Being
    0.64
     was
    0.63
     seraient
    0.62
    Act Density 0.547%

    No Known Activations