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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases that indicate emphasis or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INFORM
    -0.56
    Inform
    -0.54
     Inform
    -0.54
    inform
    -0.53
    hloromethane
    -0.53
     INFORM
    -0.52
     büyü
    -0.51
     fırs
    -0.51
     Cana
    -0.51
     gostar
    -0.50
    POSITIVE LOGITS
    +#+#
    0.71
    ThroughAttribute
    0.71
    zości
    0.70
     tuya
    0.70
     BoxFit
    0.70
    usermodel
    0.68
    vábbi
    0.66
    IntoConstraints
    0.65
    ellido
    0.64
    ApiModelProperty
    0.60
    Act Density 0.168%

    No Known Activations