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

    Neuronpedia

    INDEX
    Explanations

    words related to switches or actions involving switches

    oai_token-act-pair · gpt-3.5-turbo

    references to switches and related mechanisms or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    za
    -0.71
    vez
    -0.70
    UGH
    -0.69
    ALE
    -0.66
    Ground
    -0.66
    AMS
    -0.65
    Relations
    -0.65
    amina
    -0.64
    Behind
    -0.64
    Chicken
    -0.63
    POSITIVE LOGITS
     switch
    1.22
     switches
    1.08
    switch
    1.05
     switching
    0.86
    aroo
    0.85
    grass
    0.84
     switched
    0.82
     Switch
    0.81
    Switch
    0.81
    gear
    0.76
    Act Density 0.009%

    No Known Activations