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

    Neuronpedia

    INDEX
    Explanations

    the verb "go" to indicate action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.10
    3:0.07
    4:0.07
    5:0.08
    6:0.09
    7:0.07
    8:0.08
    9:0.09
    10:0.07
    11:0.08
    Negative Logits
    angle
    -2.33
    iece
    -2.24
    oscopic
    -2.20
     Pulitzer
    -2.15
    ebted
    -2.11
    zin
    -2.09
    writer
    -2.04
    interstitial
    -2.02
    ¢
    -2.02
    pour
    -2.00
    POSITIVE LOGITS
     secondly
    3.15
     Secondly
    2.15
     thrott
    2.12
     Fenrir
    2.07
     fundament
    2.02
     fort
    2.00
     hinder
    1.97
     blockers
    1.95
     preced
    1.92
    etheless
    1.92
    Act Density 0.000%

    No Known Activations