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

    Neuronpedia

    INDEX
    Explanations

    words related to actions, particularly those that imply connection or relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atyw
    -0.58
     Fais
    -0.58
     hold
    -0.58
    ynh
    -0.57
     clic
    -0.55
    aruh
    -0.53
     "
    -0.52
     JAXB
    -0.52
    ิส
    -0.52
     stick
    -0.51
    POSITIVE LOGITS
    setVerticalGroup
    0.91
     frequenza
    0.87
    تقاوى
    0.85
    SerializedSize
    0.82
    WriteTagHelper
    0.81
     précédents
    0.81
     insuffisamment
    0.78
     prisonniers
    0.77
     blessés
    0.76
    uscita
    0.76
    Act Density 0.530%

    No Known Activations